© 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. 122413
    Prev
    Next
    INDEX
    Explanations

    syllables ending in vowels or specific consonants

    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
    ла
    1.13
    ?
    0.91
    ला
    0.83
    !
    0.77
    ール
    0.71
    се
    0.69
    п
    0.69
    ور
    0.68
    the
    0.68
    мо
    0.68
    POSITIVE LOGITS
     not
    0.79
     arka
    0.77
    ’
    0.73
     as
    0.71
     ks
    0.71
     aster
    0.70
     are
    0.70
     kons
    0.68
     aras
    0.68
    できない
    0.68
    Activations Density 0.003%

    No Known Activations