© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148638
    Prev
    Next
    INDEX
    Explanations

    say "Australia"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     weighs
    0.41
     &
    0.40
     professionnels
    0.38
     حاج
    0.38
    naires
    0.38
     axb
    0.37
     אך
    0.37
    jár
    0.36
    শনের
    0.36
    鿷
    0.36
    POSITIVE LOGITS
    Australian
    0.68
    Austral
    0.59
     Australian
    0.58
     Aussie
    0.57
     Австра
    0.56
    Australia
    0.55
     Austral
    0.55
    澳洲
    0.54
    澳大利亚
    0.54
     Auto
    0.54
    Activations Density 0.000%

    No Known Activations