© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48878
    Prev
    Next
    INDEX
    Explanations

    dart code examples

    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
    د
    0.89
    d
    0.87
     for
    0.86
     de
    0.72
     at
    0.71
     د
    0.71
    ddd
    0.67
     del
    0.66
     FOR
    0.66
    وح
    0.65
    POSITIVE LOGITS
    ेला
    0.74
    sville
    0.70
    ı
    0.69
    ны
    0.67
    IBRARY
    0.67
    нын
    0.66
    ılarak
    0.64
     realiz
    0.63
     consta
    0.62
    setzung
    0.61
    Activations Density 0.001%

    No Known Activations