© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121105
    Prev
    Next
    INDEX
    Explanations

    language phrases

    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_27_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
     Suzhou
    0.42
     পরিচালনা
    0.42
     चीनी
    0.42
    采访
    0.41
     Interview
    0.39
    elligence
    0.39
     Any
    0.38
    ጆ
    0.38
    
    0.38
     Pizza
    0.38
    POSITIVE LOGITS
    ровкой
    0.46
     zer
    0.42
     summand
    0.40
     झलक
    0.39
    பர
    0.38
    ряз
    0.37
     настрой
    0.37
    ковы
    0.36
     پیشن
    0.36
    фак
    0.36
    Activations Density 0.016%

    No Known Activations