© 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. 49136
    Prev
    Next
    INDEX
    Explanations

    strikingly

    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
     exagger
    0.52
    ת
    0.52
    सामान्यीकृत
    0.50
    ޗ
    0.49
    یل
    0.49
    ores
    0.48
    ನಗೆ
    0.48
     sphinct
    0.47
     drips
    0.47
     ایپلی
    0.47
    POSITIVE LOGITS
    كا
    0.52
     Ме
    0.50
     toDo
    0.49
     colectivo
    0.48
     Тере
    0.46
     Джор
    0.45
     Mundo
    0.45
     Фа
    0.45
     Я
    0.45
     Пе
    0.44
    Activations Density 0.000%

    No Known Activations