© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129133
    Prev
    Next
    INDEX
    Explanations

    llibre o llista completa

    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_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ق
    1.56
    on
    1.50
     or
    1.44
    as
    1.42
     on
    1.39
    م
    1.39
    is
    1.38
    का
    1.32
    ل
    1.32
    ب
    1.30
    POSITIVE LOGITS
    likle
    0.93
    tfrac
    0.93
    <0x80>
    0.91
    те
    0.88
    <0x9B>
    0.84
    ৮
    0.83
     সুতরাং
    0.83
    ري
    0.82
    ৭
    0.82
     чувство
    0.82
    Activations Density 0.002%

    No Known Activations