© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204678
    Prev
    Next
    INDEX
    Explanations

    say thigh

    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
     piedi
    0.45
     feet
    0.44
    Feet
    0.42
     કબ
    0.40
    feet
    0.40
     ଏ
    0.39
    足
    0.39
     足
    0.39
     Feet
    0.39
    Foot
    0.38
    POSITIVE LOGITS
     thigh
    1.89
     thighs
    1.55
     Th
    1.25
     cuisses
    1.16
    Th
    1.14
     calf
    0.93
     fem
    0.91
    th
    0.90
     femoral
    0.88
     th
    0.86
    Activations Density 0.003%

    No Known Activations