© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61218
    Prev
    Next
    INDEX
    Explanations

    ut possidetis juris

    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
    ur
    0.86
    '
    0.78
     on
    0.77
    taining
    0.75
    ra
    0.75
    น
    0.73
    TimeSeries
    0.72
     that
    0.70
     कड़ी
    0.69
    ม
    0.68
    POSITIVE LOGITS
    ۵
    1.09
    5
    1.05
    4
    0.98
    يد
    0.91
    r
    0.91
    in
    0.81
    ۴
    0.80
    ranno
    0.80
    ۳
    0.80
    ۹
    0.80
    Activations Density 0.001%

    No Known Activations