© 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. 34597
    Prev
    Next
    INDEX
    Explanations

    one

    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
    م
    0.92
    ח
    0.76
    كون
    0.74
    א
    0.73
    مكن
    0.71
    مي
    0.71
    كي
    0.71
     كلام
    0.71
    از
    0.70
    اي
    0.70
    POSITIVE LOGITS
    a
    0.88
     accrued
    0.77
    ed
    0.75
    '
    0.75
     ousted
    0.73
     структуры
    0.71
    ol
    0.71
    াঃ
    0.69
    োত্তর
    0.68
    orious
    0.68
    Activations Density 0.016%

    No Known Activations