© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12001
    Prev
    Next
    INDEX
    Explanations

    eye muscles and movement

    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_13_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
    䡏
    0.53
     vara
    0.50
    estrian
    0.48
     mutta
    0.47
    restrial
    0.46
     dynasty
    0.45
     Telangana
    0.45
    穼
    0.45
     furry
    0.44
    icent
    0.44
    POSITIVE LOGITS
    Ｆ
    0.50
          
    0.48
     gaskets
    0.45
    मनी
    0.45
    Carm
    0.45
    роки
    0.45
     préc
    0.45
           
    0.44
    Ｃ
    0.44
    Mark
    0.43
    Activations Density 0.015%

    No Known Activations