© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198568
    Prev
    Next
    INDEX
    Explanations

    Parkinson's disease and Pink Floyd

    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_12_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
    {\
    0.59
     الع
    0.58
     gái
    0.54
    ：
    0.54
     ईसाई
    0.54
     c
    0.54
     ص
    0.53
    ”.
    0.53
     om
    0.52
    {}",
    0.52
    POSITIVE LOGITS
    σιν
    0.55
    торы
    0.51
    зва
    0.50
     पीछे
    0.47
    тый
    0.47
    িপূর্ণ
    0.47
    キロ
    0.47
     neurology
    0.46
    ש
    0.46
     daring
    0.46
    Activations Density 0.000%

    No Known Activations