© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38739
    Prev
    Next
    INDEX
    Explanations

    PowerPC

    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_11_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
    0.52
    ⿸
    0.46
     כדי
    0.46
     Ч
    0.45
     Чи
    0.44
    端
    0.44
    ﾀ
    0.44
     చక్కెర
    0.43
    ENE
    0.43
    ந்
    0.43
    POSITIVE LOGITS
    in
    0.77
    z
    0.59
    at
    0.54
    w
    0.52
    to
    0.50
    f
    0.50
    with
    0.50
    teman
    0.50
    on
    0.49
    l
    0.49
    Activations Density 0.000%

    No Known Activations