© 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. 130368
    Prev
    Next
    INDEX
    Explanations

    endings like -et, -us, -an, -ei, -en, -ar

    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
     \
    0.77
     for
    0.70
    ’
    0.65
    al
    0.65
    ar
    0.63
    ä
    0.63
     by
    0.63
    ส
    0.62
    0.61
     ت
    0.61
    POSITIVE LOGITS
    ين
    0.92
    هاي
    0.83
    ﺮ
    0.81
    ك
    0.80
    ﺸ
    0.76
    زي
    0.76
     Điện
    0.75
    ът
    0.73
     Máy
    0.73
    పై
    0.73
    Activations Density 0.000%

    No Known Activations