© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136236
    Prev
    Next
    INDEX
    Explanations

    Juliana Bram, Juliana Chan

    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_12_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
    ન્યા
    0.58
     ಉತ್ಪ
    0.57
     исте
    0.55
    нера
    0.55
     rück
    0.54
    anego
    0.54
    inesis
    0.53
     전
    0.52
    ഹ്ലാദ
    0.52
    enta
    0.52
    POSITIVE LOGITS
    i
    0.59
     jurnal
    0.52
    magazine
    0.51
     VARCHAR
    0.49
     A
    0.49
    Charl
    0.48
    lari
    0.48
    事前に
    0.48
    grammar
    0.47
     magazine
    0.47
    Activations Density 0.000%

    No Known Activations