© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225000
    Prev
    Next
    INDEX
    Explanations

    swatting, batting eyelashes, batting an eye

    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_10_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
    ا
    0.40
    i
    0.40
    ↵↵
    0.37
    他对
    0.35
    (),
    0.35
     ViewModel
    0.35
    。”
    0.34
    Бі
    0.34
    e
    0.34
    这
    0.34
    POSITIVE LOGITS
    ;
    0.39
    не
    0.39
    ви
    0.39
     préparation
    0.38
    рование
    0.38
    се
    0.37
     persiapan
    0.36
    я
    0.36
    erc
    0.36
    )%
    0.36
    Activations Density 0.002%

    No Known Activations