© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3373
    Prev
    Next
    INDEX
    Explanations

    words related to statistical analysis of quantitative data

    oai_token-act-pair · gemini-2.0-flash

    keyword, coefficient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    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
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -2.39
    //
    -0.63
    ⓧ
    -0.57
     figliu
    -0.54
     vicenda
    -0.54
     scolaires
    -0.54
     enfans
    -0.52
     fatica
    -0.52
     kvä
    -0.52
     fotografico
    -0.51
    POSITIVE LOGITS
     exception
    0.59
     "..\..\
    0.57
     fol
    0.54
    ophone
    0.52
     different
    0.50
    drawn
    0.50
     terri
    0.50
     VIDEOTAPE
    0.50
     god
    0.50
     pula
    0.50
    Activations Density 1.261%

    No Known Activations