© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15301
    Prev
    Next
    INDEX
    Explanations

    ductwork and its components

    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_13_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
     ചോ
    0.61
     同じ
    0.56
     seguridad
    0.55
     asking
    0.55
    Asking
    0.55
    Charging
    0.55
     sécurité
    0.54
     dezelfde
    0.54
     dina
    0.54
    錡
    0.54
    POSITIVE LOGITS
     Myerson
    0.52
    向下
    0.50
    _{
    0.49
    يروس
    0.47
    onti
    0.46
    rounds
    0.45
     intorno
    0.44
    行為
    0.43
    шина
    0.43
    ıml
    0.42
    Activations Density 0.012%

    No Known Activations