© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79014
    Prev
    Next
    INDEX
    Explanations

    suburbs of metropolitan areas

    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_31_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
     piazza
    0.46
    镇
    0.42
    პი
    0.38
     paese
    0.37
    village
    0.37
     हाईवे
    0.37
    Coastal
    0.37
    kusen
    0.37
     Caputo
    0.37
     Dorf
    0.37
    POSITIVE LOGITS
     महानगर
    0.53
    Metro
    0.51
     metro
    0.50
     Metro
    0.49
     மெட்ரோ
    0.48
     metropolitan
    0.45
    મેટ
    0.45
     <!--
    0.44
     suburbs
    0.41
     Metropolitan
    0.40
    Activations Density 0.040%

    No Known Activations