© 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
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4404
    Prev
    Next
    INDEX
    Explanations

    asia, exchange rates, spot markets

    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_39_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
     internazionale
    0.39
     अंतर्राष्ट्रीय
    0.39
     internacional
    0.39
     국제
    0.38
    (_)
    0.38
    ayın
    0.38
     সংকট
    0.37
     vyz
    0.36
     کیس
    0.36
     น้ํา
    0.36
    POSITIVE LOGITS
    дні
    0.39
     turnovers
    0.38
     electronics
    0.36
     turnover
    0.36
     Windows
    0.36
     Expressway
    0.36
    со
    0.35
     Scor
    0.35
    पत
    0.34
    癜
    0.34
    Activations Density 0.023%

    No Known Activations