© 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. 121504
    Prev
    Next
    INDEX
    Explanations

    genetic programming

    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
     It
    0.91
    It
    0.79
     for
    0.78
     it
    0.76
    de
    0.73
     You
    0.72
     For
    0.67
     \
    0.66
    you
    0.65
     be
    0.64
    POSITIVE LOGITS
    atória
    0.70
    िडेट
    0.69
    يّ
    0.67
    iénd
    0.65
    بە
    0.63
    蔗
    0.63
    ières
    0.63
    بود
    0.63
    鄔
    0.63
     álgebra
    0.62
    Activations Density 0.001%

    No Known Activations