© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41529
    Prev
    Next
    INDEX
    Explanations

    canvas context equal

    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
    ین
    0.77
    又は
    0.70
    ルの
    0.69
    ி
    0.68
    ндары
    0.66
    ту
    0.66
    (.*
    0.66
    ม
    0.66
    тельств
    0.65
    си
    0.65
    POSITIVE LOGITS
    ’
    0.96
    IN
    0.92
     as
    0.90
     I
    0.84
    EN
    0.81
     of
    0.79
    IT
    0.78
    LE
    0.73
    ”
    0.70
     =
    0.70
    Activations Density 0.000%

    No Known Activations