© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66871
    Prev
    Next
    INDEX
    Explanations

    dominant vs. recessive

    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_41_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
     файла
    0.39
    acin
    0.37
     Оле
    0.37
     бушлай
    0.36
    ugins
    0.36
     Sì
    0.35
    aban
    0.35
    ɣ
    0.35
    FIG
    0.34
     фай
    0.34
    POSITIVE LOGITS
     dominant
    2.14
    dominant
    1.94
     dominante
    1.82
     Domin
    1.75
    Domin
    1.68
     domin
    1.63
     dominate
    1.62
     dominating
    1.52
     dominates
    1.50
    domin
    1.41
    Activations Density 0.004%

    No Known Activations