© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40838
    Prev
    Next
    INDEX
    Explanations

    enum definitions

    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
    5
    0.86
    9
    0.84
    ER
    0.82
    4
    0.81
    3
    0.75
    8
    0.75
    6
    0.75
    il
    0.75
    un
    0.74
    im
    0.72
    POSITIVE LOGITS
     이미
    0.79
    ת
    0.71
     чет
    0.70
    ozione
    0.68
    '
    0.68
     تحقیق
    0.66
     eſ
    0.66
     scompar
    0.65
     callous
    0.64
     gén
    0.63
    Activations Density 0.006%

    No Known Activations