© 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. 91776
    Prev
    Next
    INDEX
    Explanations

    numbers followed by sztuk

    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
    ’
    0.84
    :
    0.83
    ”
    0.79
     as
    0.77
    ：
    0.75
    se
    0.70
    ene
    0.65
    ח
    0.63
    غ
    0.59
    দ্র
    0.57
    POSITIVE LOGITS
    ু
    0.75
    ޏ
    0.69
    videos
    0.68
     Mekong
    0.68
    cursos
    0.67
    био
    0.67
    ᱑
    0.67
    Immun
    0.66
    виси
    0.66
    )){
    0.65
    Activations Density 0.017%

    No Known Activations