© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44885
    Prev
    Next
    INDEX
    Explanations

    dozing, doujinshi, dozer, doji, doxazosin

    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_3_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
     of
    0.82
     in
    0.70
    ন
    0.65
     zuvor
    0.64
    在
    0.62
    ор
    0.61
    㗽
    0.59
     nerveux
    0.58
    0.58
     pédicule
    0.58
    POSITIVE LOGITS
     be
    0.88
    1
    0.84
    I
    0.79
    ä
    0.78
    ip
    0.75
    á
    0.73
    ک
    0.71
    c
    0.69
    Ꮸ
    0.67
    g
    0.67
    Activations Density 0.002%

    No Known Activations