© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27456
    Prev
    Next
    INDEX
    Explanations

    LG products

    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
    0.78
     permanente
    0.77
    7
    0.75
    na
    0.73
    ↵↵↵
    0.73
    az
    0.72
     presente
    0.72
    ud
    0.71
    0.71
    0.70
    POSITIVE LOGITS
    い
    0.97
    ων
    0.85
    ان
    0.81
    つ
    0.79
    त्
    0.77
    های
    0.77
    itute
    0.74
    الیا
    0.74
    त्या
    0.73
    in
    0.73
    Activations Density 0.001%

    No Known Activations