© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49898
    Prev
    Next
    INDEX
    Explanations

    user input prompts

    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
    t
    0.79
    ó
    0.71
    on
    0.69
    ón
    0.67
    ́i
    0.66
    th
    0.64
    τών
    0.63
    ᴏ
    0.62
    фі
    0.61
    ónicas
    0.60
    POSITIVE LOGITS
     Кстати
    0.66
    вае
    0.65
     Многие
    0.63
     ຈ
    0.61
     क्यो
    0.59
     craindre
    0.59
     ক
    0.59
     צ
    0.58
     Даже
    0.58
     ขณะ
    0.57
    Activations Density 0.020%

    No Known Activations