© 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. 86414
    Prev
    Next
    INDEX
    Explanations

    foreign characters and abbreviations

    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
    ン
    0.90
    ett
    0.82
    nö
    0.79
    aj
    0.78
    í
    0.78
    ai
    0.76
    änder
    0.74
    н
    0.74
    au
    0.71
    of
    0.71
    POSITIVE LOGITS
    ไม่
    0.71
     imprison
    0.71
    প
    0.69
    {[\
    0.69
    𓂀
    0.69
     الْم
    0.68
    你會
    0.68
     Consultado
    0.66
    গ্রাফ
    0.65
     (\
    0.64
    Activations Density 0.000%

    No Known Activations