© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84080
    Prev
    Next
    INDEX
    Explanations

    uv followed by iste, igny, or ia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    .
    1.34
    Ь
    1.13
    _
    1.12
     الفلسطيني
    1.08
    ._
    1.04
    ?
    1.03
     nich
    1.02
    zata
    1.02
    Ы
    1.02
     was
    1.01
    POSITIVE LOGITS
    in
    2.08
    n
    2.08
    은
    2.06
    ش
    1.97
    ar
    1.94
    न
    1.89
     a
    1.87
    is
    1.86
    a
    1.83
    ج
    1.83
    Activations Density 0.000%

    No Known Activations