© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30440
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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_10_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
    G
    0.91
    M
    0.85
    Window
    0.80
    3
    0.77
    '
    0.76
    AI
    0.73
    ON
    0.73
    0
    0.71
    Time
    0.66
    Social
    0.66
    POSITIVE LOGITS
    ية
    0.87
    يك
    0.73
     bijvoorbeeld
    0.71
     eine
    0.70
     einer
    0.70
    جي
    0.69
    ِّف
    0.68
     بي
    0.68
     حتى
    0.68
     ఒక
    0.67
    Activations Density 0.022%

    No Known Activations