© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125447
    Prev
    Next
    INDEX
    Explanations

    ah, ow sounds

    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
     squared
    0.77
     a
    0.75
    માં
    0.73
    -
    0.73
    are
    0.71
    ่า
    0.69
     {
    0.68
    as
    0.68
    arı
    0.68
     squaring
    0.67
    POSITIVE LOGITS
    ش
    0.87
    ли
    0.82
    '
    0.82
    الش
    0.78
    在
    0.74
    もら
    0.74
    ال
    0.71
    ш
    0.71
    n
    0.70
    ন
    0.69
    Activations Density 0.000%

    No Known Activations