© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83916
    Prev
    Next
    INDEX
    Explanations

    command execution

    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_0_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
    '
    1.95
    ي
    1.57
    י
    1.49
    い
    1.43
    ри
    1.39
    \
    1.30
     мнение
    1.28
    то
    1.27
     точке
    1.27
    رة
    1.25
    POSITIVE LOGITS
     as
    1.52
     it
    1.50
     be
    1.45
    ad
    1.39
    Y
    1.36
    ing
    1.35
    M
    1.34
    C
    1.33
    V
    1.32
     (
    1.31
    Activations Density 0.002%

    No Known Activations