© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    pi (π) and formulas

    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_15_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
     Tolkien
    0.57
    When
    0.56
    If
    0.54
    Spot
    0.51
    Sleeping
    0.51
    Corn
    0.50
    沧
    0.50
    Let
    0.49
    Cuando
    0.49
    Ste
    0.49
    POSITIVE LOGITS
     PQ
    0.55
    ми
    0.53
    st
    0.52
    amore
    0.52
    mo
    0.51
    뉴스
    0.51
    pq
    0.50
    ,=
    0.50
     comprising
    0.50
    p
    0.50
    Activations Density 0.000%

    No Known Activations