© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218997
    Prev
    Next
    INDEX
    Explanations

    prince/principality

    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_47_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
    侙
    0.37
    口气
    0.37
    ധ്യമ
    0.36
    idlo
    0.36
     الحق
    0.34
    ിലോ
    0.34
    
    0.34
     Haq
    0.33
    盆
    0.33
    숟
    0.33
    POSITIVE LOGITS
     prince
    1.77
     Prince
    1.73
     princes
    1.68
    Prince
    1.62
     Princes
    1.59
     princ
    1.48
     PRIN
    1.48
     प्रिंस
    1.48
     príncipe
    1.46
     прин
    1.44
    Activations Density 0.000%

    No Known Activations