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
© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-27B-IT
41-GEMMASCOPE-2-TRANSCODER-262K
63165
Prev
Next
MODEL
41-gemmascope-2-transcoder-262k
Source/SAE
INDEX
Go
Explanations
conspiracy theories: white genocide, cultural Marxism, love jihad, great replacement, cow protection
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-27b-it/transcoder_all/layer_41_width_262k_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-3-27b-it/41-gemmascope-2-transcoder-262k/63165?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-3-27b-it/41-gemmascope-2-transcoder-262k/63165?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
nine
0.59
９
0.59
九
0.54
九
0.54
৯
0.53
۹
0.53
9
0.53
۹
0.53
Nine
0.52
ninety
0.52
POSITIVE LOGITS
৭৭
0.39
oxygen
0.38
umbo
0.38
練習
0.36
7
0.36
๗
0.36
Hopkins
0.35
ileno
0.35
喷
0.35
training
0.35
Act
ivations
Density 0.003%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
