© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201069
    Prev
    Next
    INDEX
    Explanations

    geographic

    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_46_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
    MDET
    0.40
    FindingsRequest
    0.36
    oclaw
    0.36
    Von
    0.35
    BackendAuth
    0.35
    蓍
    0.35
     locksmith
    0.34
    关
    0.34
     वडील
    0.33
    ⅛
    0.33
    POSITIVE LOGITS
     geographic
    2.52
     geographical
    2.42
     geograf
    2.41
     geography
    2.36
     Geographical
    2.33
     Geography
    2.31
     Geographic
    2.31
    地理
    2.31
     географи
    2.30
    Geography
    2.27
    Activations Density 0.003%

    No Known Activations