© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159508
    Prev
    Next
    INDEX
    Explanations

    sv or м followed by word

    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_2_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
    t
    1.38
    У
    1.09
    the
    1.08
     one
    0.96
     बिक्री
    0.96
    d
    0.96
    и
    0.96
    기
    0.95
     the
    0.92
            
    0.90
    POSITIVE LOGITS
    ק
    1.23
    ológicas
    0.91
    kách
    0.87
    tható
    0.85
     terminó
    0.82
     הראש
    0.81
    బ్‌
    0.80
    த்திலிருந்து
    0.80
    рачи
    0.80
    ０
    0.79
    Activations Density 0.003%

    No Known Activations