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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124963
    Prev
    Next
    INDEX
    Explanations

    rank correlation, sum statistic, test

    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
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.69
    e
    0.61
    uera
    0.55
     сучас
    0.54
    i
    0.54
    蛯
    0.54
    excludeFolder
    0.54
    ið
    0.53
    uridad
    0.52
     সেপ্ট
    0.51
    POSITIVE LOGITS
     to
    1.08
     on
    0.92
    یس
    0.70
    не
    0.68
    ید
    0.68
    ↵↵
    0.67
     from
    0.64
    DA
    0.64
     votes
    0.64
    PA
    0.64
    Activations Density 0.000%

    No Known Activations