© 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. 49927
    Prev
    Next
    INDEX
    Explanations

    manicures/pedicures

    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
     Candida
    0.33
    リーチ
    0.33
    ictwo
    0.32
     libre
    0.32
    벨
    0.32
     Metro
    0.32
     Outlet
    0.31
     втори
    0.31
    
    0.31
    nunique
    0.31
    POSITIVE LOGITS
     टैंक
    0.37
    Cleaner
    0.36
     ট্যাঙ্ক
    0.36
     ined
    0.33
     निदान
    0.33
     जरुर
    0.33
     Cle
    0.32
    RestTemplate
    0.32
    صول
    0.32
     Татар
    0.32
    Activations Density 0.055%

    No Known Activations