© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64325
    Prev
    Next
    INDEX
    Explanations

    ley lines and ancestral knowledge

    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_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
     ブルー
    0.39
    owntown
    0.37
    ":
    0.37
    ブルー
    0.36
     agu
    0.35
     aga
    0.35
     দেখতে
    0.34
    uzzo
    0.34
     suna
    0.34
    컷
    0.34
    POSITIVE LOGITS
     Dream
    0.92
    Dream
    0.91
     dream
    0.84
     DREAM
    0.78
    dream
    0.77
    梦
    0.76
     dreaming
    0.70
    夢
    0.70
     꿈
    0.68
     ड्रीम
    0.66
    Activations Density 0.023%

    No Known Activations