© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166674
    Prev
    Next
    INDEX
    Explanations

    while

    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_31_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
     G
    0.39
     reduz
    0.38
    ارض
    0.38
    LuaPush
    0.37
     लोहा
    0.36
     विलय
    0.36
     deport
    0.36
    毎年
    0.36
     além
    0.34
     丶
    0.34
    POSITIVE LOGITS
    ivali
    0.40
    vart
    0.39
     ಕೂ
    0.38
    చ్
    0.37
    হৃত
    0.36
    vár
    0.36
     independence
    0.36
     Essentially
    0.35
    ầu
    0.35
     awaited
    0.35
    Activations Density 0.001%

    No Known Activations