© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108433
    Prev
    Next
    INDEX
    Explanations

    alternate

    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_2_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
    .
    0.94
     услу
    0.84
    он
    0.79
    o
    0.78
     rozwiąz
    0.73
     škola
    0.72
    ní
    0.70
     кілько
    0.70
     внутрен
    0.69
     экономи
    0.68
    POSITIVE LOGITS
    (
    1.09
     powied
    0.88
     (
    0.87
    T
    0.87
    ים
    0.86
    લ
    0.82
    ما
    0.79
    치가
    0.79
    B
    0.79
    of
    0.77
    Activations Density 0.001%

    No Known Activations