© 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. 79660
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ل
    2.11
    સ
    1.97
    л
    1.68
    t
    1.67
    in
    1.66
    ي
    1.65
    د
    1.62
    s
    1.61
    v
    1.52
    ک
    1.49
    POSITIVE LOGITS
     playwright
    1.34
    ’
    1.27
    1.19
    0
    1.18
    THAT
    1.16
     rebuke
    1.15
    UST
    1.13
    ND
    1.13
     medication
    1.13
    ITO
    1.13
    Activations Density 0.000%

    No Known Activations