© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 825
    Prev
    Next
    INDEX
    Explanations

    code. It seems to trigger on hexidecimal and other kinds of code syntax, as well as xml and version numbering

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sportivo
    -0.48
     hoarse
    -0.46
     downwards
    -0.46
    NG
    -0.46
    AN
    -0.46
     Reducing
    -0.45
    CH
    -0.44
    FH
    -0.44
    tomia
    -0.44
     chairmen
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.98
    bootstrapcdn
    0.94
    帖最后由
    0.91
     NSCoder
    0.90
    ReusableCell
    0.86
     ModelExpression
    0.84
     AssemblyCulture
    0.81
    mybatisplus
    0.81
    awtextra
    0.81
    MigrationBuilder
    0.78
    Activations Density 9.170%

    No Known Activations