© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12619
    Prev
    Next
    INDEX
    Explanations

    sentences about school assignments, enrollments or transfers

    oai_token-act-pair · gemini-2.0-flash

    Santa

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للاسماء
    -0.69
     disambiguazione
    -0.68
     ویکی‌پدیای
    -0.66
    GHIJKLM
    -0.62
    protoimpl
    -0.61
     AssemblyCompany
    -0.61
    aarrggbb
    -0.58
    AnimationsModule
    -0.58
     FontWeight
    -0.56
    <?
    -0.56
    POSITIVE LOGITS
     Santa
    0.96
    Santa
    0.85
     Cal
    0.78
     Ventura
    0.76
     SANTA
    0.74
     Gole
    0.72
     santa
    0.71
    santa
    0.70
    Cal
    0.69
     San
    0.68
    Activations Density 4.400%

    No Known Activations