© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27195
    Prev
    Next
    INDEX
    Explanations

    Jinzhou, Jinlong, Jin Dong, Jinmeiyō, Jinsei, Jin Mao, Jin Dynasty, jinja

    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_10_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
    r
    1.02
    ۔
    0.93
    s
    0.91
    ла
    0.85
    with
    0.84
    urs
    0.81
    ي
    0.81
    ذ
    0.79
    ја
    0.78
    ง
    0.77
    POSITIVE LOGITS
     reorganize
    1.01
     have
    0.89
     organize
    0.89
    ס
    0.88
     diminue
    0.87
     incentivize
    0.87
    ो
    0.86
     reorganized
    0.85
    inę
    0.83
    Duplicates
    0.82
    Activations Density 0.003%

    No Known Activations