© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9561
    Prev
    Next
    INDEX
    Explanations

    code snippets with github links and regex

    oai_token-act-pair · gemini-2.0-flash

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <em>
    -1.00
    <i>
    -0.73
    حياتها
    -0.50
     reda
    -0.49
    lidean
    -0.48
     _
    -0.44
     ó
    -0.43
     escol
    -0.42
    /*
    -0.41
    CodeDom
    -0.41
    POSITIVE LOGITS
     AssemblyTitle
    0.85
    ✨:
    0.71
    mschrijving
    0.67
     **/
    0.63
    例文帳に追加
    0.62
     Monfieur
    0.61
    ImageContext
    0.60
    ensuremath
    0.59
     باسم
    0.58
     Theſe
    0.58
    Activations Density 1.586%

    No Known Activations