© 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. 39707
    Prev
    Next
    INDEX
    Explanations

    android operating system

    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
    ä
    0.79
    SetActive
    0.72
    o
    0.68
    om
    0.64
    நோய்
    0.63
    ow
    0.63
     受
    0.63
    PL
    0.62
     သင်
    0.62
    ing
    0.61
    POSITIVE LOGITS
     conglomerate
    0.56
     channeled
    0.55
     кристал
    0.54
     performer
    0.53
     роки
    0.52
     saker
    0.51
    тся
    0.51
     машина
    0.51
     mennesker
    0.51
     производи
    0.50
    Activations Density 0.001%

    No Known Activations