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

    Neuronpedia

    Jacobian LensNEW
    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. 7479
    Prev
    Next
    INDEX
    Explanations

    hands moving or holding

    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
     Milch
    0.36
     Freund
    0.35
     Ani
    0.35
    倾
    0.34
     trás
    0.34
     mong
    0.34
    生まれた
    0.34
    牴
    0.34
     Monter
    0.33
     Breite
    0.33
    POSITIVE LOGITS
     hand
    1.98
    Hand
    1.73
     Hand
    1.73
    hand
    1.67
    手
    1.67
     HAND
    1.49
    HAND
    1.43
     دست
    1.38
     handheld
    1.34
     手
    1.32
    Activations Density 0.058%

    No Known Activations