© 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. 8611
    Prev
    Next
    INDEX
    Explanations

    at the heart lies

    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
    Ala
    0.25
     દવા
    0.25
     他
    0.23
     તેની
    0.22
    ie
    0.22
    ylan
    0.22
     ব্যবহারে
    0.22
     Walker
    0.21
    2
    0.21
    Binary
    0.21
    POSITIVE LOGITS
    ాన్
    0.27
     леп
    0.24
     minhas
    0.24
    וס
    0.24
    烦
    0.24
     partes
    0.23
    ש
    0.23
     pleural
    0.23
     juicy
    0.23
     chromospheres
    0.23
    Activations Density 0.038%

    No Known Activations