© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139817
    Prev
    Next
    INDEX
    Explanations

    South Africa

    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_37_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
     Pretoria
    0.81
     Transvaal
    0.75
     Gauteng
    0.56
     Kruger
    0.55
     Johannesburg
    0.54
    Afrika
    0.53
     Boer
    0.52
    🇿
    0.52
     apartheid
    0.50
     Durban
    0.49
    POSITIVE LOGITS
     Vamp
    0.39
    ям
    0.38
    minim
    0.37
     Poland
    0.37
     Baran
    0.36
    ęt
    0.36
    掺
    0.36
     കലാ
    0.35
     finalText
    0.35
     mysticism
    0.34
    Activations Density 0.000%

    No Known Activations