© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171534
    Prev
    Next
    INDEX
    Explanations

    physical actions of the body

    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_20_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
    atorias
    0.51
    鉾
    0.45
    ποίη
    0.44
    USED
    0.44
    ைகளைக்
    0.43
    পেক্ষ
    0.43
    Football
    0.42
    кість
    0.41
    before
    0.41
    盃
    0.41
    POSITIVE LOGITS
     convex
    0.49
     creativity
    0.49
     substantive
    0.48
     pett
    0.45
     covari
    0.45
     zeal
    0.44
     habitable
    0.44
     modestly
    0.44
     zealous
    0.44
     powinien
    0.43
    Activations Density 0.001%

    No Known Activations