© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83231
    Prev
    Next
    INDEX
    Explanations

    slaying, spraying, laying, praying, belaying

    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_0_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
    for
    1.80
    8
    1.74
    0
    1.67
     for
    1.66
    7
    1.63
     For
    1.47
    4
    1.41
    6
    1.39
    For
    1.38
    <0x0D>
    1.31
    POSITIVE LOGITS
    '
    2.56
    ა
    1.95
    า
    1.86
    কে
    1.73
    ט
    1.70
    ก
    1.61
    सँग
    1.54
    та
    1.51
    い
    1.50
    માં
    1.49
    Activations Density 0.000%

    No Known Activations