© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81817
    Prev
    Next
    INDEX
    Explanations

    hydraulic components and concepts

    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_0_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
    ación
    1.69
    -
    1.66
    них
    1.48
    чение
    1.39
    ний
    1.37
    lık
    1.36
    ية
    1.35
    ки
    1.32
    ме
    1.31
    ен
    1.30
    POSITIVE LOGITS
    t
    1.55
    e
    1.54
    Y
    1.50
    R
    1.48
    K
    1.47
    ال
    1.46
    L
    1.43
    ر
    1.42
    ت
    1.42
    a
    1.38
    Activations Density 0.000%

    No Known Activations