© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139645
    Prev
    Next
    INDEX
    Explanations

    AI language models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     indisc
    0.40
    apsingToolbar
    0.37
    cin
    0.36
     SIC
    0.35
    rollup
    0.35
    ﺻ
    0.35
    لات
    0.35
     Cinque
    0.34
    וט
    0.33
    走了
    0.33
    POSITIVE LOGITS
     существо
    0.42
     создания
    0.42
     Unidos
    0.41
     анализ
    0.40
    漑
    0.40
     створення
    0.39
    drawiam
    0.39
    anded
    0.38
    uksia
    0.38
     создание
    0.38
    Activations Density 0.000%

    No Known Activations