© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180721
    Prev
    Next
    INDEX
    Explanations

    torch.randn, device, relu

    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_29_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
     cleanly
    0.39
    concatenate
    0.38
    :“
    0.38
    ிரி
    0.38
     seamlessly
    0.38
     obvi
    0.38
     शुरुआ
    0.37
    şiv
    0.37
     magically
    0.37
    မူ
    0.37
    POSITIVE LOGITS
    नांक
    0.38
     Noble
    0.36
    Noble
    0.35
    ਔ
    0.35
     বিদ্যা
    0.34
    
    0.34
    ermanfaat
    0.34
     COMMENTS
    0.34
     बनाता
    0.34
     ஆப
    0.34
    Activations Density 0.003%

    No Known Activations