© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175817
    Prev
    Next
    INDEX
    Explanations

    2

    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_24_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
    भेद
    0.15
    땠
    0.15
    cameraId
    0.14
     الواحده
    0.14
     मिट
    0.14
     Behind
    0.14
     ग्राम
    0.14
     Tert
    0.14
    arket
    0.14
     கர்ப்ப
    0.14
    POSITIVE LOGITS
     všechny
    0.15
    示意
    0.15
     wszystkie
    0.15
     všetky
    0.15
    cuna
    0.14
     š
    0.14
    +|
    0.14
     ін
    0.14
    enhuma
    0.14
    起
    0.14
    Activations Density 0.003%

    No Known Activations