© 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. 121530
    Prev
    Next
    INDEX
    Explanations

    network design

    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
     in
    1.03
     to
    1.02
     at
    0.92
     It
    0.91
    س
    0.75
     from
    0.68
     for
    0.68
     There
    0.66
     dari
    0.66
    在
    0.64
    POSITIVE LOGITS
    the
    0.78
    r
    0.75
    e
    0.73
    t
    0.64
    ти
    0.59
    isce
    0.59
    ή
    0.59
     هیڅ
    0.59
    InMillis
    0.57
    omegal
    0.57
    Activations Density 0.003%

    No Known Activations