© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199351
    Prev
    Next
    INDEX
    Explanations

    paclitaxel, attack roll, city names

    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_15_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
    ﺍ
    0.52
     friendly
    0.50
     аз
    0.49
     lengthening
    0.49
     Friendly
    0.47
     जा
    0.47
     ניתן
    0.47
     convient
    0.46
     съем
    0.46
    ৩
    0.46
    POSITIVE LOGITS
    LIBRARY
    0.52
    X
    0.48
    code
    0.48
    BURY
    0.47
    اید
    0.46
    RY
    0.46
    ग्गा
    0.46
    owali
    0.46
    ناس
    0.46
    AKT
    0.46
    Activations Density 0.000%

    No Known Activations