Downloads · 30 days
8
17% of all-time downloads
gemma-3-27b-activation-oracle-step-35000
annasoli/gemma-3-27b-activation-oracle-step-35000
gemma-3-27b-activation-oracle-step-35000 is a machine learning model from annasoli. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
All-time downloads
47
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 98%
At a glance
- Library
- peft
- Model type
- gemma3
- Access
- Public
- Created
- Dec 20, 2025
- Updated
- Dec 20, 2025
- SHA
- b32b7236
Base models
Model card
From the Hugging Face model README
LoRA Adapter for SAE Introspection
This is a LoRA (Low-Rank Adaptation) adapter trained for SAE (Sparse Autoencoder) introspection tasks.
Base Model
- Base Model:
google/gemma-3-27b-it - Adapter Type: LoRA
- Task: SAE Feature Introspection
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
# Load base model and tokenizer
base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-27b-it")
tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-27b-it")
# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "annasoli/gemma-3-27b-activation-oracle-step-35000")
Training Details
This adapter was trained using the lightweight SAE introspection training script to help the model understand and explain SAE features through activation steering.
- Library
- peft
- Type
- gemma3
- Created
- Dec 20, 2025
- Updated
- Dec 20, 2025