© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4571
    Prev
    Next
    INDEX
    Explanations

    South African cities and places

    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_38_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
    PPTV
    0.41
    omechanics
    0.37
     PyQt
    0.36
     australia
    0.35
     Panchayat
    0.35
    <()>
    0.35
    umlahan
    0.34
    ेशंस
    0.34
    $&$-
    0.34
     ensu
    0.34
    POSITIVE LOGITS
     Gauteng
    1.13
     KwaZulu
    1.01
     Stellen
    0.98
     Pretoria
    0.93
     Afrika
    0.93
    Afrika
    0.91
     Johannesburg
    0.89
    Cape
    0.87
     Durban
    0.87
     Cape
    0.85
    Activations Density 0.019%

    No Known Activations