© 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. 121689
    Prev
    Next
    INDEX
    Explanations

    log management

    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
    Negative Logits
    ו
    0.76
    (
    0.64
    ного
    0.62
    ėjo
    0.60
     Sapir
    0.57
    ర్‌
    0.54
    ۴
    0.54
    ছে
    0.54
    ное
    0.54
     Tattha
    0.54
    POSITIVE LOGITS
     to
    0.87
    _
    0.87
    ।
    0.70
     are
    0.68
    '
    0.65
     angels
    0.61
    ur
    0.60
    س
    0.60
    计划
    0.59
     ہیں۔
    0.59
    Activations Density 0.001%

    No Known Activations