© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46126
    Prev
    Next
    INDEX
    Explanations

    Dhillon Kannabhiran

    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_3_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
    是
    0.80
    ి
    0.76
    కు
    0.76
    는
    0.71
    is
    0.70
    ي
    0.66
    は
    0.66
    ти
    0.66
    "，
    0.64
    ી
    0.64
    POSITIVE LOGITS
    もら
    0.88
    テナンス
    0.77
    stargo
    0.71
    もちろん
    0.69
    kala
    0.68
     sanitaria
    0.68
    ST
    0.68
    ことを
    0.66
    ?
    0.66
     to
    0.66
    Activations Density 0.000%

    No Known Activations