© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226503
    Prev
    Next
    INDEX
    Explanations

    Marjorie Liu, Marjorie Elmore, anything goes

    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_6_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
    >
    0.95
    ant
    0.84
    r
    0.83
    IOR
    0.81
     titul
    0.79
    al
    0.78
     exuber
    0.75
     VEGFR
    0.75
     fluvial
    0.74
     nhàng
    0.74
    POSITIVE LOGITS
    л
    0.99
    ா
    0.95
    на
    0.94
    ా
    0.93
    с
    0.92
    ا
    0.91
    า
    0.89
     are
    0.88
    č
    0.88
    N
    0.84
    Activations Density 0.000%

    No Known Activations