© 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. 135208
    Prev
    Next
    INDEX
    Explanations

    trajectories

    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
    Not in Any Lists

    No Comments

    Negative Logits
     can
    1.52
    0
    1.41
    ع
    1.41
    ль
    1.33
    ש
    1.32
    в
    1.29
    ك
    1.29
     is
    1.25
    the
    1.24
    ق
    1.23
    POSITIVE LOGITS
    ak
    0.99
    TES
    0.98
    ität
    0.98
    ťaž
    0.98
     alteraciones
    0.97
    n
    0.96
    ens
    0.95
    rinth
    0.93
     regra
    0.93
     dificultades
    0.93
    Activations Density 0.001%

    No Known Activations