© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91084
    Prev
    Next
    INDEX
    Explanations

    good question/statement

    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
    י
    0.73
    [
    0.64
    <
    0.63
    不知道
    0.61
    ו
    0.61
    尽管
    0.59
    当
    0.59
     tinha
    0.58
     veel
    0.57
    年轻
    0.57
    POSITIVE LOGITS
     are
    0.85
    s
    0.83
    ма
    0.82
    ką
    0.76
    ضای
    0.75
    sleeping
    0.73
    ные
    0.71
    sources
    0.71
    soldiers
    0.71
    стный
    0.68
    Activations Density 0.001%

    No Known Activations