© 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. 127995
    Prev
    Next
    INDEX
    Explanations

    destructive

    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
    .
    0.70
     apporter
    0.69
     incendio
    0.69
     extérieures
    0.65
     élarg
    0.63
     auditions
    0.62
    ’
    0.62
     participer
    0.61
    م
    0.61
    ası
    0.61
    POSITIVE LOGITS
    t
    0.75
    с
    0.75
    ton
    0.72
    ticket
    0.71
    ty
    0.68
     Counting
    0.67
    domain
    0.65
    td
    0.64
    screen
    0.64
    ті
    0.62
    Activations Density 0.001%

    No Known Activations