© 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. 126229
    Prev
    Next
    INDEX
    Explanations

    dog whistle

    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
     electrón
    0.81
     Цуки
    0.68
    correctAns
    0.66
    GoObject
    0.66
     aterriz
    0.65
    ්
    0.65
     Алексей
    0.64
     humains
    0.64
    もら
    0.64
    カード
    0.64
    POSITIVE LOGITS
    ac
    0.83
    at
    0.78
    2
    0.77
    ized
    0.76
    im
    0.76
    em
    0.75
    ik
    0.72
    ado
    0.72
    ade
    0.71
    ام
    0.71
    Activations Density 0.003%

    No Known Activations