© 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. 11539
    Prev
    Next
    INDEX
    Explanations

    lifting heavy objects

    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
    িনের
    0.29
    िला
    0.28
     vida
    0.27
    processes
    0.27
    слан
    0.27
    ˵
    0.27
     life
    0.27
     entreg
    0.27
    ',
    0.26
     avión
    0.26
    POSITIVE LOGITS
     tablette
    0.32
     স্ট
    0.31
    कडील
    0.31
    xit
    0.31
    Stat
    0.30
    St
    0.30
    cił
    0.30
    зой
    0.29
     С
    0.29
     סט
    0.29
    Activations Density 0.016%

    No Known Activations