© 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. 40789
    Prev
    Next
    INDEX
    Explanations

    commercial exchange name

    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
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.79
    ാരി
    0.67
    ാ
    0.64
    ק
    0.62
    '\
    0.61
    matic
    0.61
    ';...
    0.60
    '،
    0.58
    isture
    0.57
    ни
    0.57
    POSITIVE LOGITS
    re
    0.84
     variar
    0.74
     commerciaux
    0.74
    ર
    0.70
    ра
    0.68
     אחת
    0.67
    $.
    0.65
     участок
    0.65
     etap
    0.64
     commercial
    0.63
    Activations Density 0.031%

    No Known Activations