© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54756
    Prev
    Next
    INDEX
    Explanations

    unsteady flow, circumference, address

    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_30_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
    лость
    0.38
    ?\
    0.38
     outstanding
    0.35
    aldi
    0.34
     tonic
    0.34
     Sald
    0.34
    equal
    0.33
     तुरु
    0.33
     $+$
    0.33
     outfit
    0.33
    POSITIVE LOGITS
    час
    0.35
    ırken
    0.33
     dayan
    0.33
    celer
    0.33
     numerosi
    0.33
    NSString
    0.32
    FromString
    0.32
    шенные
    0.32
     atténuées
    0.31
     applaud
    0.31
    Activations Density 0.000%

    No Known Activations