© 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. 51175
    Prev
    Next
    INDEX
    Explanations

    count of documents

    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
    يك
    0.67
    ли
    0.66
    يات
    0.66
    يس
    0.65
    يف
    0.63
    يد
    0.62
    են
    0.62
    g
    0.61
    ىن
    0.59
    وس
    0.58
    POSITIVE LOGITS
     важ
    0.70
     rozwią
    0.67
    )
    0.64
     HAVE
    0.63
     THAT
    0.61
     zdjęcia
    0.61
    </i>
    0.58
     have
    0.57
     solve
    0.56
     якщо
    0.56
    Activations Density 0.014%

    No Known Activations