© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41607
    Prev
    Next
    INDEX
    Explanations

    LeetCode code

    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_22_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
    aruhi
    0.31
    தேச
    0.30
    ುತ್ತೇವೆ
    0.30
     سنه
    0.28
    㫣
    0.28
     gover
    0.28
    ত্রী
    0.27
    SOME
    0.27
    aysia
    0.27
    hesized
    0.27
    POSITIVE LOGITS
     रहीम
    0.30
     +
    0.29
     millioner
    0.29
     видео
    0.29
     ут
    0.29
    之路
    0.28
     Wur
    0.28
     mattis
    0.28
     alight
    0.28
     tout
    0.27
    Activations Density 0.004%

    No Known Activations