© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35589
    Prev
    Next
    INDEX
    Explanations

    portfolio

    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
     seater
    0.43
    䛺
    0.38
     முன்
    0.36
     meyd
    0.36
    跗
    0.35
     synt
    0.34
     condens
    0.34
    썩
    0.34
     சது
    0.33
     जनप्रतिनि
    0.33
    POSITIVE LOGITS
     portfolio
    3.25
     portfolios
    2.97
    portfolio
    2.95
     Portfolio
    2.94
    Portfolio
    2.92
     portefeuille
    2.14
     cartera
    1.84
     порт
    1.75
     पोर्ट
    1.66
    ポート
    1.57
    Activations Density 0.083%

    No Known Activations