© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195423
    Prev
    Next
    INDEX
    Explanations

    Feature

    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_46_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
     dört
    0.44
     группа
    0.39
     migration
    0.39
     четыре
    0.38
     vaginale
    0.38
     Таким
    0.37
     groep
    0.37
     такому
    0.37
    ላት
    0.36
    ㍍
    0.36
    POSITIVE LOGITS
     avenues
    0.41
     Fa
    0.37
     dara
    0.37
     Leads
    0.35
     Space
    0.35
     sẵn
    0.35
     complained
    0.35
    thur
    0.35
     Routes
    0.35
     ArrayIndex
    0.34
    Activations Density 0.002%

    No Known Activations