© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231591
    Prev
    Next
    INDEX
    Explanations

    target market

    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_6_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
     مي‌
    0.98
    સ્થા
    0.98
    volle
    0.95
    ور
    0.95
    i
    0.95
     в
    0.94
    ного
    0.93
    brado
    0.93
    وريا
    0.92
    un
    0.91
    POSITIVE LOGITS
     to
    1.00
    ä
    0.89
    د
    0.82
     Diversity
    0.80
    \
    0.80
     Unfortunately
    0.78
     Criticism
    0.77
     It
    0.75
     Warnings
    0.75
    elling
    0.73
    Activations Density 0.000%

    No Known Activations