© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46609
    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_13_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
    ر
    0.46
    antal
    0.46
     (
    0.43
    ج
    0.43
    row
    0.42
    There
    0.41
    r
    0.41
    Surface
    0.40
    atorias
    0.40
    utions
    0.39
    POSITIVE LOGITS
    Попис
    0.64
    𝙋
    0.59
    WMat
    0.57
     />);
    0.57
     Hôm
    0.56
     pptd
    0.56
     arrhyth
    0.56
    𒄩
    0.55
     sepd
    0.55
    markUp
    0.55
    Activations Density 0.000%

    No Known Activations