© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18797
    Prev
    Next
    INDEX
    Explanations

    easy-to-use library

    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_40_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
    昧
    0.38
     Nodes
    0.38
    ことです
    0.36
    楽しく
    0.35
    Nodes
    0.35
     印
    0.34
     هوا
    0.34
    xhtml
    0.34
     ഏറെ
    0.34
    $[
    0.34
    POSITIVE LOGITS
     articul
    0.46
    lukan
    0.38
    ascular
    0.38
    するか
    0.38
     wide
    0.37
    wn
    0.37
     স্ক
    0.37
     ausge
    0.36
     dış
    0.36
     lám
    0.36
    Activations Density 0.002%

    No Known Activations