© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34837
    Prev
    Next
    INDEX
    Explanations

    John F. Kennedy

    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_7_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
    -
    0.78
    ४
    0.76
    ༥
    0.73
    os
    0.73
    -/
    0.70
    à
    0.69
    "</
    0.68
    ai
    0.67
    ją
    0.67
    ८
    0.66
    POSITIVE LOGITS
     by
    0.59
    成员
    0.55
    ↵↵
    0.54
    ت
    0.52
    ین
    0.52
    кои
    0.52
    ید
    0.52
     некоторым
    0.52
    ders
    0.51
    空氣
    0.50
    Activations Density 0.002%

    No Known Activations