© 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. 38782
    Prev
    Next
    INDEX
    Explanations

    speech recognition and synthesis

    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
    ي
    0.95
    i
    0.85
    <0xA3>
    0.79
    يته
    0.78
    to
    0.75
     KPI
    0.75
    <0x80>
    0.73
    <0x8C>
    0.73
    <0x81>
    0.70
    in
    0.68
    POSITIVE LOGITS
    ä
    0.79
    ร
    0.70
     disabilities
    0.67
     aktivitas
    0.67
    لی
    0.66
     been
    0.65
    স
    0.65
     pemerintah
    0.64
    ্দ
    0.64
    ス
    0.64
    Activations Density 0.003%

    No Known Activations