© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208870
    Prev
    Next
    INDEX
    Explanations

    absolute best, finest, priority, unit

    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
    ς
    0.62
    ים
    0.61
     средства
    0.57
     недавно
    0.57
    SubDirectoryPath
    0.57
     ול
    0.55
     moglie
    0.55
    ↵↵
    0.55
     potencia
    0.55
    ן
    0.55
    POSITIVE LOGITS
    t
    0.78
    ت
    0.73
    ان
    0.72
    an
    0.67
    ari
    0.67
    RO
    0.67
    onne
    0.64
    v
    0.63
    し
    0.63
     can
    0.63
    Activations Density 0.002%

    No Known Activations