© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63408
    Prev
    Next
    INDEX
    Explanations

    legs and feet

    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_46_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
     covenants
    0.37
    俆
    0.37
    รั
    0.36
    ૃહ
    0.35
     handcuffed
    0.34
    riya
    0.34
     covenant
    0.33
    笵
    0.33
    */)
    0.33
    䡛
    0.32
    POSITIVE LOGITS
     legs
    3.28
     Legs
    2.91
    legs
    2.73
    腿
    2.64
    脚
    2.61
     leg
    2.55
    腳
    2.47
     ноги
    2.45
     feet
    2.39
     chân
    2.25
    Activations Density 0.072%

    No Known Activations