© 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. 39741
    Prev
    Next
    INDEX
    Explanations

    nature.com links and articles

    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
     οι
    0.62
    ం
    0.60
    いた
    0.60
     பெரும்பாலான
    0.56
     be
    0.55
    éd
    0.54
     of
    0.53
    6
    0.53
     quais
    0.52
     понимаю
    0.52
    POSITIVE LOGITS
    ра
    0.86
    ש
    0.72
    لي
    0.69
    し
    0.68
     Controle
    0.62
    的设计
    0.61
    šel
    0.61
    in
    0.61
    IN
    0.60
     Servicio
    0.60
    Activations Density 0.001%

    No Known Activations