© 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. 27460
    Prev
    Next
    INDEX
    Explanations

    clerical work and clergy

    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
    her
    0.78
    ل
    0.75
    ar
    0.71
    itores
    0.66
    onder
    0.64
    uie
    0.64
    lo
    0.63
    have
    0.63
    indeterminate
    0.63
    allocate
    0.62
    POSITIVE LOGITS
    ’
    0.81
    RO
    0.70
    EN
    0.69
    '
    0.63
    ס
    0.62
    ्स
    0.61
    ný
    0.61
    德
    0.60
     is
    0.59
    AL
    0.59
    Activations Density 0.001%

    No Known Activations