© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104065
    Prev
    Next
    INDEX
    Explanations

    operative, perioperative, anaesthetic

    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_1_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
    '
    1.66
    _
    1.40
    ,
    1.19
    IE
    1.05
    I
    1.02
    ING
    1.02
    在
    1.01
    ت
    1.00
     badge
    0.99
     deserial
    0.97
    POSITIVE LOGITS
    ى
    1.80
    n
    1.50
    리
    1.44
    f
    1.41
    or
    1.33
    u
    1.30
    re
    1.30
    m
    1.27
    o
    1.26
    ップ
    1.25
    Activations Density 0.000%

    No Known Activations