© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4109
    Prev
    Next
    INDEX
    Explanations

    IR, air, Irish

    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_39_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
    от
    0.39
     sorts
    0.38
    ost
    0.38
    ovas
    0.36
    sby
    0.36
    ی
    0.36
    maybe
    0.36
    onie
    0.36
     maybe
    0.35
    ϳ
    0.35
    POSITIVE LOGITS
    ंगाई
    0.39
    auté
    0.38
    ĕç
    0.38
    ichlet
    0.38
     상관
    0.38
     acondicionado
    0.36
     Ciência
    0.36
    viendo
    0.35
    frying
    0.35
     Somewhat
    0.35
    Activations Density 0.136%

    No Known Activations