© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130405
    Prev
    Next
    INDEX
    Explanations

    domestication

    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_6_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
     It
    1.01
    ling
    0.99
    in
    0.85
     be
    0.79
     to
    0.77
    ੋ
    0.77
     of
    0.75
    amas
    0.74
     ر
    0.74
    ada
    0.73
    POSITIVE LOGITS
    ת
    1.09
    ה
    1.08
     jednego
    1.03
    ي
    1.02
     других
    0.96
    i
    0.89
     каждого
    0.89
     potencialmente
    0.88
    न
    0.84
    ஷ
    0.83
    Activations Density 0.000%

    No Known Activations