© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38822
    Prev
    Next
    INDEX
    Explanations

    South American 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_11_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
     {
    0.33
     orang
    0.33
     McLaughlin
    0.31
     andre
    0.31
    ,"@
    0.31
     ndị
    0.30
     co
    0.30
    โน
    0.30
     Andrew
    0.30
    นำ
    0.30
    POSITIVE LOGITS
    up
    0.41
    deletion
    0.38
    nas
    0.38
    ciencia
    0.38
    represents
    0.38
    dziel
    0.37
    இந்திய
    0.37
    labelled
    0.36
    personalised
    0.36
    珵
    0.35
    Activations Density 0.003%

    No Known Activations