© 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. 92587
    Prev
    Next
    INDEX
    Explanations

    excuse me

    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
    し
    0.71
    .
    0.64
     So
    0.61
    s
    0.61
     (
    0.59
    เสีย
    0.57
     क्योंकि
    0.54
     tiba
    0.54
    <0x80>
    0.53
    ซึ่ง
    0.53
    POSITIVE LOGITS
    ف
    0.75
    ي
    0.70
    y
    0.68
    etown
    0.65
     apartamentos
    0.65
    fords
    0.64
    丰
    0.64
    ed
    0.63
    我们
    0.63
    etum
    0.63
    Activations Density 0.001%

    No Known Activations