© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 989
    Prev
    Next
    INDEX
    Explanations

    carrying and lifting 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_40_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
    onato
    0.37
     सुरेश
    0.34
    ﮗ
    0.32
    "?>
    0.31
     charter
    0.30
    телем
    0.30
    楢
    0.30
     үш
    0.30
     обу
    0.30
    直し
    0.29
    POSITIVE LOGITS
     carrying
    1.97
     carry
    1.83
     Carrying
    1.79
    carrying
    1.70
    carry
    1.68
     Carry
    1.67
     carries
    1.66
     carried
    1.62
    Carry
    1.62
     حمل
    1.56
    Activations Density 0.124%

    No Known Activations