© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48461
    Prev
    Next
    INDEX
    Explanations

    Mauna Kea or Na Pali

    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_10_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
    h
    0.85
    ق
    0.84
     of
    0.79
    "
    0.70
    넬
    0.66
    说
    0.66
     Experten
    0.65
    <0x0D>
    0.64
     Cui
    0.64
    jf
    0.63
    POSITIVE LOGITS
     نمی‌
    0.66
    に変
    0.65
     ሥራ
    0.63
     revisiting
    0.62
     प्रसंस्करण
    0.61
     producing
    0.61
     می‌کنند
    0.61
    ės
    0.60
     تولید
    0.59
    ٹرز
    0.59
    Activations Density 0.000%

    No Known Activations