© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44822
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

    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_13_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
    :
    0.17
    เหนือ
    0.17
    ，
    0.17
     [
    0.16
     (
    0.16
    ।”
    0.16
     amber
    0.16
     thread
    0.16
    ?”
    0.16
    Thread
    0.15
    POSITIVE LOGITS
    ലു
    0.17
    शासित
    0.17
    ﾝ
    0.17
     ಕೈ
    0.17
     Malgré
    0.17
    信念
    0.17
    தியே
    0.17
     uttered
    0.16
     سٹ
    0.16
     கழு
    0.16
    Activations Density 0.008%

    No Known Activations