© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51429
    Prev
    Next
    INDEX
    Explanations

    quaint

    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_10_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
    ER
    0.82
    '
    0.77
    ター
    0.74
    0
    0.74
    ers
    0.74
    ة
    0.74
    un
    0.73
    aya
    0.71
    ’
    0.71
    is
    0.65
    POSITIVE LOGITS
     cables
    0.74
     wires
    0.70
     windings
    0.70
    🎌
    0.70
     år
    0.69
    ی
    0.68
    чок
    0.67
     созда
    0.66
     lleve
    0.66
     stitched
    0.65
    Activations Density 0.000%

    No Known Activations