© 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. 47583
    Prev
    Next
    INDEX
    Explanations

    one

    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
    ت
    0.88
    த்தில்
    0.78
    ত
    0.78
    ри
    0.77
    त
    0.75
    ار
    0.75
    т
    0.74
     شيء
    0.71
    ot
    0.70
     ريا
    0.70
    POSITIVE LOGITS
    Якщо
    0.95
    Про
    0.87
    Если
    0.87
    {
    0.87
    Pokud
    0.83
    Ба
    0.82
    2
    0.79
    نا
    0.79
    Бу
    0.79
    defines
    0.78
    Activations Density 0.002%

    No Known Activations