© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14480
    Prev
    Next
    INDEX
    Explanations

    geographic location

    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_13_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
    n
    0.64
    every
    0.60
    minimum
    0.57
    discount
    0.55
    decre
    0.54
    i
    0.54
    Hardware
    0.54
    `
    0.52
     headache
    0.52
    cargar
    0.51
    POSITIVE LOGITS
     Johannesburg
    0.66
    рон
    0.63
     passieren
    0.62
     situés
    0.62
     Tasmania
    0.61
     geográfica
    0.61
     Brisbane
    0.60
     geograf
    0.60
     LOCATION
    0.60
     menjalankan
    0.60
    Activations Density 0.054%

    No Known Activations