© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110776
    Prev
    Next
    INDEX
    Explanations

    Chiang Mai, Chiang Kai-shek

    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_2_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
    '
    1.48
    و
    1.05
    orems
    1.02
    没有
    0.99
    ће
    0.96
     entsprechenden
    0.95
    да
    0.95
     даних
    0.94
    е
    0.93
     einem
    0.92
    POSITIVE LOGITS
    that
    1.73
     that
    1.66
    W
    1.41
    an
    1.29
    J
    1.27
    F
    1.24
     que
    1.23
    ۹
    1.23
    B
    1.21
     to
    1.20
    Activations Density 0.000%

    No Known Activations