© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53111
    Prev
    Next
    INDEX
    Explanations

    headings and structure

    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_30_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
     “‘
    0.38
     мину
    0.36
     Flüss
    0.36
    ('"
    0.35
    agliari
    0.35
     jendela
    0.35
    waitForIdleSync
    0.35
    液
    0.34
    ވެ
    0.34
    Ordinate
    0.34
    POSITIVE LOGITS
    ！！！
    0.38
     আমরা
    0.35
    Funding
    0.35
     Con
    0.35
    ！)
    0.35
    PTI
    0.34
     使用
    0.34
     begonnen
    0.34
    。<
    0.34
    ？
    0.34
    Activations Density 0.001%

    No Known Activations