© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80313
    Prev
    Next
    INDEX
    Explanations

    closing connections

    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_31_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
     exhaust
    0.42
     arşiv
    0.39
     Xen
    0.39
     Exhaust
    0.39
     exhaustion
    0.38
    臭
    0.38
     unters
    0.35
     glutamate
    0.35
     freshness
    0.34
    ادم
    0.34
    POSITIVE LOGITS
    ⎡
    0.44
     могли
    0.40
     serviços
    0.38
    adrat
    0.38
     pourrait
    0.37
    [&
    0.37
     podría
    0.36
    Var
    0.36
     الاش
    0.36
    owns
    0.36
    Activations Density 0.003%

    No Known Activations