© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63269
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     shark
    1.19
     Shark
    1.16
     sharks
    1.14
    Shark
    1.12
     Sharks
    1.00
    shark
    0.98
    鯊
    0.89
    鲨
    0.88
     Great
    0.79
    🦈
    0.74
    POSITIVE LOGITS
     Captain
    0.77
    Captain
    0.76
     captain
    0.73
    captain
    0.70
     captains
    0.66
     capitaine
    0.59
     capitán
    0.59
     कप्तान
    0.55
     ক্যাপ্টেন
    0.52
    Capt
    0.48
    Activations Density 0.004%

    No Known Activations