© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196590
    Prev
    Next
    INDEX
    Explanations

    specific words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    뛴
    0.35
    ದಲ್ಲ
    0.33
    >>();
    0.33
    ⴷ
    0.33
    ཊ
    0.32
    الس
    0.32
     गिफ्ट
    0.32
    බන්ධ
    0.32
    ابط
    0.31
    虏
    0.31
    POSITIVE LOGITS
    iram
    0.35
     auss
    0.34
    え
    0.33
     kr
    0.32
    ega
    0.32
     Gott
    0.32
    ore
    0.31
    ori
    0.30
     ${_
    0.30
    Got
    0.30
    Activations Density 0.012%

    No Known Activations