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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12276
    Prev
    Next
    INDEX
    Explanations

    chunks of code like table definitions, array manipulations and XML returns.

    oai_token-act-pair · gemini-2.0-flash

    row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Row
    -0.76
     row
    -0.75
     ROW
    -0.75
    Row
    -0.74
     Rows
    -0.74
     rows
    -0.69
    ItemBackground
    -0.68
    row
    -0.65
    rows
    -0.62
     rowCount
    -0.60
    POSITIVE LOGITS
    ברס
    0.49
    (&:
    0.48
    OOTDTY
    0.48
     kny
    0.46
    相关文章
    0.46
     Assn
    0.45
    ujin
    0.45
     back
    0.44
    StoredProcedure
    0.44
    centiles
    0.44
    Activations Density 23.577%

    No Known Activations