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
0-GEMMASCOPE-TRANSCODER-16K
7170
Prev
Next
MODEL
0-gemmascope-transcoder-16k
Source/SAE
INDEX
Go
Explanations
terms related to legal agreements and conditions for use
oai_token-act-pair · gemini-2.0-flash
No Scores
BE
np_max-act · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.0.ln2.hook_normalized
Architecture
jumprelu_transcoder
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-transcoder-16k/7170?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-transcoder-16k/7170?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
DE
-1.40
WE
-1.39
BE
-1.37
SE
-1.36
RE
-1.33
LE
-1.31
NE
-1.30
TE
-1.28
JE
-1.27
TE
-1.25
POSITIVE LOGITS
e
0.64
re
0.63
o
0.59
ve
0.58
PMailer
0.57
de
0.56
De
0.55
ta
0.52
<bos>
0.50
po
0.50
Act
ivations
Density 0.839%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
