© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124876
    Prev
    Next
    INDEX
    Explanations

    St. Basil's Cathedral, Joint Arthritis, Basel III

    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_3_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
    n
    0.96
    x
    0.76
     housings
    0.73
    benzoimidazole
    0.73
     qualify
    0.69
    nR
    0.68
    t
    0.68
     nmea
    0.68
     nessuno
    0.67
    ל
    0.67
    POSITIVE LOGITS
    س
    1.13
    ↵↵
    0.94
    с
    0.89
    ني
    0.85
    </h3>
    0.83
    斯
    0.75
    )。
    0.72
    ↵↵↵
    0.71
    內
    0.70
    行
    0.69
    Activations Density 0.000%

    No Known Activations