Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
21-GEMMASCOPE-TRANSCODER-16K
5995
Prev
Next
MODEL
21-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
standard terms and acronyms, especially in technical or scientific contexts
oai_token-act-pair · gemini-2.0-flash
No Scores
capital letters at the beginning of words
np_token-act-pair-logits · gpt-4o-mini
No Scores
Letters
np_max-act-logits · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope/layer_21/width_16k
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/5995?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/21-gemmascope-transcoder-16k/5995?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
myſelf
-1.24
Theſe
-1.23
itſelf
-1.23
Reſ
-1.17
Houſe
-1.16
Majefty
-1.12
ſelves
-1.10
Efq
-1.09
―――――
-1.06
ſelf
-1.04
POSITIVE LOGITS
M
1.02
H
1.01
D
0.98
L
0.97
G
0.96
F
0.95
S
0.91
R
0.90
W
0.90
T
0.89
Act
ivations
Density 15.900%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
