© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33809
    Prev
    Next
    INDEX
    Explanations

    say "affairs"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    松
    0.41
    뇌
    0.40
     松
    0.38
    ோட
    0.35
    ㄵ
    0.34
    زل
    0.33
    توان
    0.33
    mények
    0.33
    緎
    0.33
    Dots
    0.32
    POSITIVE LOGITS
     affairs
    3.31
     Affairs
    2.98
     affair
    2.83
     AFFAIRS
    2.63
     affaires
    2.50
     Affair
    2.45
     affaire
    2.39
    affaire
    2.13
     AFFA
    2.08
     अफेयर्स
    1.85
    Activations Density 0.004%

    No Known Activations