© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3332
    Prev
    Next
    INDEX
    Explanations

    village and town locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     hebat
    0.77
    im
    0.75
     esto
    0.75
     suatu
    0.73
    ippy
    0.70
    }'.
    0.70
    ева
    0.70
     الخاص
    0.69
    arza
    0.68
    ক্স
    0.67
    POSITIVE LOGITS
    та
    1.15
    speople
    1.14
    Town
    0.81
    krieg
    0.79
    town
    0.78
    ्यूट
    0.75
    瘩
    0.73
     Township
    0.72
    munic
    0.72
    snd
    0.71
    Activations Density 0.064%

    No Known Activations