© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201264
    Prev
    Next
    INDEX
    Explanations

    foot

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bergh
    0.46
    Wearing
    0.42
    bergs
    0.40
     Wearing
    0.39
    Tim
    0.38
    R
    0.38
    Tun
    0.38
    berg
    0.38
    bu
    0.37
    Economic
    0.37
    POSITIVE LOGITS
     foot
    0.68
    foot
    0.61
     Foot
    0.61
    Foot
    0.60
     Fuß
    0.57
     voet
    0.57
     足
    0.56
     FOOT
    0.55
     footh
    0.54
    足
    0.52
    Activations Density 0.001%

    No Known Activations