© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
GEMMA-3-4B-IT · 2-GEMMASCOPE-2-TRANSCODER-16K · 8 ｜ Neuronpedia
Home
Gemma-3-4B-IT
2-GEMMASCOPE-2-TRANSCODER-16K
8
Prev
Next
MODEL
2-gemmascope-2-transcoder-16k
Source/SAE
INDEX
Go
Explanations
No Explanations Found
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-4b-it/2-gemmascope-2-transcoder-16k/8?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-4b-it/2-gemmascope-2-transcoder-16k/8?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
законом
1.68
ка
1.66
夊
1.57
員
1.56
کننده
1.56
далее
1.55
jší
1.53
Правда
1.51
1.50
)]);
1.44
POSITIVE LOGITS
یب
1.87
ल
1.85
en
1.83
macht
1.76
ن
1.73
m
1.70
ל
1.68
ताकत
1.63
on
1.62
ویه
1.62
Act
ivations
Density 0.110%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
