© 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. 86901
    Prev
    Next
    INDEX
    Explanations

    secret key

    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
    ב
    0.85
    ре
    0.83
    ра
    0.82
    ール
    0.82
    ла
    0.81
    ہ
    0.80
    の
    0.76
    いる
    0.75
    ের
    0.75
    악
    0.75
    POSITIVE LOGITS
    o
    0.78
    ley
    0.73
    ess
    0.69
    ene
    0.69
     Wasn
    0.68
    ce
    0.68
    ete
    0.66
    ater
    0.65
    I
    0.65
    EN
    0.65
    Activations Density 0.002%

    No Known Activations