© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232428
    Prev
    Next
    INDEX
    Explanations

    compare adjacent elements and swap

    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_32_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
     Statute
    0.37
    Rating
    0.36
     Ratings
    0.36
    姮
    0.36
    Cord
    0.36
    傊
    0.35
     площад
    0.35
     khắc
    0.35
     век
    0.35
    Cordial
    0.35
    POSITIVE LOGITS
    rocessor
    0.37
     주
    0.36
     дере
    0.36
    achella
    0.36
    óis
    0.36
     श्रेणियों
    0.35
    
    0.35
     subsystems
    0.35
     setTasks
    0.35
    actyl
    0.35
    Activations Density 0.001%

    No Known Activations