© 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. 209981
    Prev
    Next
    INDEX
    Explanations

    prime minister

    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
    ik
    0.96
    iz
    0.95
    '
    0.91
    ud
    0.88
    and
    0.81
    ig
    0.79
    ut
    0.78
    asters
    0.77
    ate
    0.75
    M
    0.74
    POSITIVE LOGITS
     kaisi
    0.65
     meriye
    0.65
    的安全
    0.62
    セキュリティ
    0.61
    ため
    0.61
     আপনাকে
    0.61
     فونبیټ
    0.61
     Huxley
    0.59
     فونبټ
    0.58
     هاکي
    0.58
    Activations Density 0.000%

    No Known Activations