© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42109
    Prev
    Next
    INDEX
    Explanations

    nomination, nominee, programs

    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
    기
    1.05
    在
    1.01
    م
    0.94
    기와
    0.93
    a
    0.92
    ج
    0.81
    f
    0.80
    ين
    0.80
    و
    0.80
    న్
    0.79
    POSITIVE LOGITS
    0
    0.86
     jou
    0.79
     on
    0.75
     nominee
    0.68
     off
    0.67
     nomin
    0.64
     quasi
    0.64
     its
    0.64
     govern
    0.63
     nomination
    0.63
    Activations Density 0.003%

    No Known Activations