© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101497
    Prev
    Next
    INDEX
    Explanations

    tensor parallelism

    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_14_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
    ૬
    0.53
     nouveaux
    0.52
     faits
    0.52
     desapar
    0.52
     DNIs
    0.51
     Gass
    0.51
     soups
    0.50
     electrolytes
    0.49
     misconceptions
    0.49
     convective
    0.48
    POSITIVE LOGITS
    v
    0.54
    เล่น
    0.52
    f
    0.52
    erei
    0.50
    vet
    0.49
    (...)
    0.48
    ong
    0.48
     شكل
    0.48
    run
    0.48
     খেলে
    0.48
    Activations Density 0.004%

    No Known Activations