© 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. 6992
    Prev
    Next
    INDEX
    Explanations

    sudden movements and reactions

    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
    Walk
    0.67
    เดิน
    0.59
     Walk
    0.59
     walk
    0.57
    Walking
    0.55
    走到
    0.54
    walk
    0.52
    歩
    0.52
     berjalan
    0.50
     camin
    0.50
    POSITIVE LOGITS
     jumping
    0.80
     leaping
    0.78
     leaped
    0.69
     jumped
    0.69
     Jumping
    0.69
     leaps
    0.68
     leapt
    0.68
     jumps
    0.66
     jump
    0.66
     leap
    0.63
    Activations Density 0.099%

    No Known Activations