© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210879
    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_20_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
    france
    0.49
    ze
    0.46
    зыва
    0.45
     contra
    0.45
    duc
    0.44
    <0x83>
    0.43
    few
    0.43
    comb
    0.43
    partials
    0.42
    idental
    0.42
    POSITIVE LOGITS
    栻
    0.58
     ট্যাবলেট
    0.46
    َہ
    0.44
    チャンネル
    0.43
    东南
    0.42
    耒
    0.42
    ኬ
    0.40
     аў
    0.39
    мія
    0.39
     Künst
    0.39
    Activations Density 0.000%

    No Known Activations