© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123771
    Prev
    Next
    INDEX
    Explanations

    train and test data splitting

    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_3_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
    да
    0.75
    ’
    0.75
    就
    0.75
    ي
    0.73
     in
    0.73
    i
    0.72
     bonsai
    0.71
     socialist
    0.70
     convivial
    0.69
    ח
    0.69
    POSITIVE LOGITS
    for
    0.75
    ا
    0.73
    fe
    0.71
     powied
    0.71
    as
    0.64
    to
    0.62
    af
    0.62
     przyczyn
    0.61
    fully
    0.60
    foration
    0.59
    Activations Density 0.003%

    No Known Activations