© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4393
    Prev
    Next
    INDEX
    Explanations

    route

    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_40_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
    +"/"+
    0.40
     বিশ্র
    0.39
     বিশ্রাম
    0.37
     nisu
    0.36
    會在
    0.35
    /_
    0.35
     LANC
    0.35
     विद्व
    0.34
     রহিম
    0.34
    anski
    0.34
    POSITIVE LOGITS
    पर्या
    0.36
     purchasing
    0.35
    檬
    0.35
     acquist
    0.34
     miraculously
    0.34
     purchases
    0.34
    购买
    0.34
     государство
    0.34
     requisito
    0.33
     embarked
    0.33
    Activations Density 0.002%

    No Known Activations