© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93902
    Prev
    Next
    INDEX
    Explanations

    SQL keywords

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TO
    0.62
    IN
    0.61
    s
    0.61
    sf
    0.59
    ws
    0.58
    sa
    0.57
    NI
    0.57
    RI
    0.57
    nc
    0.57
    wp
    0.57
    POSITIVE LOGITS
     се
    0.52
     seam
    0.50
     se
    0.48
     Se
    0.45
     Caldwell
    0.44
     seams
    0.44
     centro
    0.43
     Verfahren
    0.43
     Drosophila
    0.42
     repertoire
    0.41
    Activations Density 0.001%

    No Known Activations