© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207472
    Prev
    Next
    INDEX
    Explanations

    shareholder / holder

    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_10_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
     linen
    0.67
     faute
    0.67
     insecticide
    0.66
     l
    0.63
    יות
    0.63
     viewfinder
    0.63
    刄
    0.61
     auto
    0.61
     zombie
    0.61
     butterfly
    0.60
    POSITIVE LOGITS
    0
    0.80
    6
    0.78
    :
    0.77
    ;
    0.76
    2
    0.75
    3
    0.73
    Name
    0.71
    7
    0.71
    CS
    0.70
    4
    0.69
    Activations Density 0.001%

    No Known Activations