© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53123
    Prev
    Next
    INDEX
    Explanations

    text alignment center

    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_31_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
    algorith
    0.44
    ফিকুল
    0.42
    Unlike
    0.38
    fragment
    0.38
    ()<<
    0.37
    ggplot
    0.37
    HttpGet
    0.37
     algorith
    0.37
    kurat
    0.36
    Philipp
    0.36
    POSITIVE LOGITS
    煂
    0.45
     table
    0.41
     столб
    0.38
    สนาม
    0.38
     wav
    0.37
     tabled
    0.37
     ಬ್ಯಾ
    0.37
    物业
    0.37
     നിര
    0.37
     波
    0.37
    Activations Density 0.002%

    No Known Activations