© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17777
    Prev
    Next
    INDEX
    Explanations

    medical history

    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_40_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
     კიდ
    0.42
    债券
    0.39
    Workbook
    0.36
    Damage
    0.36
    തമായ
    0.36
     Prot
    0.35
    交互
    0.35
    跛
    0.34
    வர்களை
    0.34
    僑
    0.34
    POSITIVE LOGITS
     history
    0.73
     History
    0.64
    history
    0.64
     इतिहास
    0.64
    History
    0.59
     histories
    0.59
     истории
    0.59
     HISTORY
    0.59
     past
    0.58
    HISTORY
    0.56
    Activations Density 0.052%

    No Known Activations