© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79852
    Prev
    Next
    INDEX
    Explanations

    Bilbao, Bilbo, Bilious, Basilica, Basil

    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_0_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
    И
    1.59
    Y
    1.33
    İ
    1.30
    ö
    1.23
    ین
    1.20
    ل
    1.19
    ?
    1.17
    Я
    1.17
    Ž
    1.15
    ata
    1.14
    POSITIVE LOGITS
    at
    1.66
    to
    1.59
    та
    1.59
    is
    1.57
     as
    1.50
    as
    1.48
    s
    1.48
    didn
    1.43
    y
    1.43
    ある
    1.41
    Activations Density 0.000%

    No Known Activations