© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195185
    Prev
    Next
    INDEX
    Explanations

    passenger vehicles and transport

    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_9_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
     (
    1.01
    ש
    1.01
    n
    0.82
    -
    0.80
    ли
    0.77
    kost
    0.76
    kast
    0.75
    uose
    0.73
    ווי
    0.73
    kke
    0.71
    POSITIVE LOGITS
    è
    0.90
    ﺧ
    0.80
    ابی
    0.80
    ạ
    0.80
    ø
    0.80
    ى
    0.77
     تبدیلی
    0.77
     Ичиго
    0.76
    𝙥
    0.76
    一来
    0.75
    Activations Density 0.002%

    No Known Activations