© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3940
    Prev
    Next
    INDEX
    Explanations

    words appearing in academic or scientific texts

    oai_token-act-pair · gemini-2.0-flash

    Java programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Stä
    -0.52
    arakhand
    -0.47
     Backward
    -0.45
    AndEndTag
    -0.45
    cripcion
    -0.45
    amazonaws
    -0.45
    .(*
    -0.45
    lık
    -0.45
     Hecho
    -0.44
     groupName
    -0.43
    POSITIVE LOGITS
    <bos>
    1.33
    RTEX
    0.80
     مشين
    0.69
    '])){
    0.68
    UnusedPrivate
    0.67
    principalTable
    0.67
    openConnection
    0.65
     समीक्षाओं
    0.65
    Demografía
    0.65
    出版年
    0.64
    Activations Density 25.857%

    No Known Activations