© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137709
    Prev
    Next
    INDEX
    Explanations

    passport

    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_46_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
     玉
    0.44
    cuna
    0.38
     Caffeine
    0.37
    稲
    0.36
    KERNEL
    0.36
    昆
    0.35
     வேளாண்
    0.34
    㚅
    0.34
    ignment
    0.34
    कमा
    0.34
    POSITIVE LOGITS
     passport
    3.25
     Passport
    3.25
    Passport
    3.19
     passports
    3.05
    passport
    3.03
     पासपोर्ट
    2.78
     পাসপোর্ট
    2.72
     паспо
    2.67
     паспорт
    2.67
     pas
    2.09
    Activations Density 0.001%

    No Known Activations