© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136368
    Prev
    Next
    INDEX
    Explanations

    International acronyms and scales

    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_12_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
    ia
    0.58
    number
    0.56
    ma
    0.54
    ūr
    0.52
    답
    0.51
    year
    0.50
    smoking
    0.49
     संकेत
    0.49
    ouk
    0.49
     Albums
    0.49
    POSITIVE LOGITS
    ת
    0.59
     Chebyshev
    0.59
    Après
    0.58
    Egy
    0.58
     definiert
    0.57
     από
    0.57
     seism
    0.57
     EDA
    0.56
    ამის
    0.56
    Brian
    0.55
    Activations Density 0.000%

    No Known Activations