© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19545
    Prev
    Next
    INDEX
    Explanations

    TikTok URLs and usernames

    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_15_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
     снова
    0.56
     thorac
    0.54
     શક્ય
    0.53
     "),
    0.53
    他
    0.52
     এইভাবে
    0.50
     उपकरण
    0.50
     Traum
    0.50
     всеки
    0.49
     evanes
    0.49
    POSITIVE LOGITS
    ards
    0.49
    家電
    0.49
    COR
    0.47
    pflicht
    0.45
    CUR
    0.45
    ନ୍ତ
    0.44
    品番
    0.44
    齑
    0.44
    VERSION
    0.43
    ços
    0.43
    Activations Density 0.000%

    No Known Activations