© 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-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0xAF>
    0.40
    ​
    0.39
    ';
    0.37
    漓
    0.36
    %\
    0.35
     unmodified
    0.35
     مرف
    0.35
    
    0.34
     Игорь
    0.34
    '=>'','
    0.34
    POSITIVE LOGITS
     Políticas
    0.40
     гре
    0.39
    ഗത
    0.39
     Bü
    0.38
     Página
    0.38
    elben
    0.38
    unitary
    0.38
    geteilt
    0.38
     Baked
    0.37
    kezi
    0.37
    Activations Density 0.000%

    No Known Activations