© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45932
    Prev
    Next
    INDEX
    Explanations

    finish the following sentence

    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_13_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
    o
    0.54
    ه
    0.52
    EST
    0.49
    یره
    0.49
    类型
    0.48
    ادر
    0.48
    e
    0.48
     heterogeneous
    0.47
    s
    0.47
    هر
    0.47
    POSITIVE LOGITS
     إذا
    0.59
     Fmat
    0.59
     Normdatei
    0.54
    Notify
    0.54
     addBook
    0.53
    Cham
    0.52
    Books
    0.50
     ファイル
    0.49
     ရက်
    0.48
     BOOKS
    0.48
    Activations Density 0.000%

    No Known Activations