© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57640
    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_11_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
    Mir
    0.64
    𝒕
    0.63
    Pur
    0.58
    植物
    0.57
    <0x0D>
    0.56
     tristeza
    0.56
    pouring
    0.55
    შირ
    0.55
    ਟ
    0.54
     Mir
    0.54
    POSITIVE LOGITS
     до
    0.59
    sentation
    0.53
     он
    0.53
     ре
    0.52
    ată
    0.49
    ăț
    0.49
    adó
    0.49
     efficacy
    0.48
     on
    0.48
     кон
    0.48
    Activations Density 0.000%

    No Known Activations