© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21145
    Prev
    Next
    INDEX
    Explanations

    health and illness

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    体
    1.27
    體
    1.17
    체
    1.14
     체
    1.13
     体
    0.98
     thể
    0.95
    体的
    0.86
    體的
    0.84
    체를
    0.72
    체가
    0.71
    POSITIVE LOGITS
    康
    0.55
     복
    0.53
     Kang
    0.50
    複
    0.49
    Kang
    0.49
     Кан
    0.48
    Complex
    0.47
    복
    0.46
    复
    0.46
     Complex
    0.45
    Activations Density 0.004%

    No Known Activations