© 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. 85447
    Prev
    Next
    INDEX
    Explanations

    Invasive Ductal CarcinomaInvasive Ductal Carcinoma (IIBA)

    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
    Negative Logits
    很
    0.80
    ర
    0.71
    F
    0.70
    uv
    0.68
    advertising
    0.68
    uan
    0.67
    Parameter
    0.67
    ी
    0.67
    Table
    0.66
    ร
    0.66
    POSITIVE LOGITS
    (
    0.86
    as
    0.75
    $
    0.73
    {
    0.73
    ar
    0.70
     ciekaw
    0.70
    arbeiten
    0.70
    و
    0.69
    стью
    0.68
    ЕНИЕ
    0.68
    Activations Density 0.001%

    No Known Activations