© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137506
    Prev
    Next
    INDEX
    Explanations

    settings, permissions, authorization

    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_12_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
    し
    0.63
     نزدیک
    0.58
    ведите
    0.55
    ポー
    0.55
     ولی
    0.54
    کم
    0.52
    renderCamera
    0.51
     ખે
    0.50
    cèle
    0.50
    زمانہ
    0.50
    POSITIVE LOGITS
     goal
    0.53
     gaji
    0.50
    攢
    0.49
     Tiki
    0.46
     goalie
    0.46
    iga
    0.45
     dupla
    0.44
    3
    0.44
     Halloween
    0.43
     saldo
    0.43
    Activations Density 0.001%

    No Known Activations