© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176711
    Prev
    Next
    INDEX
    Explanations

    loops or range statements

    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_20_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
     boomers
    0.41
     mètre
    0.39
    鈣
    0.39
     methacrylate
    0.39
    achadh
    0.39
     continuité
    0.39
    醂
    0.38
    ษัท
    0.38
     continuidade
    0.37
    Homework
    0.37
    POSITIVE LOGITS
     bookstore
    0.40
     zalo
    0.37
    isbn
    0.37
     Town
    0.36
     Mish
    0.36
     beit
    0.35
    ']);
    0.35
    ばかり
    0.35
    Después
    0.35
     (_.
    0.35
    Activations Density 0.003%

    No Known Activations