© 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-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119313
    Prev
    Next
    INDEX
    Explanations

    play, theater, theatre, drama

    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_38_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
     الممل
    0.36
    熊猫
    0.35
    రో
    0.34
     muñ
    0.34
    ظيم
    0.34
    £
    0.34
     Concerto
    0.34
    $.;
    0.34
     yelled
    0.34
    ຮູ້
    0.33
    POSITIVE LOGITS
     theatre
    1.55
     theater
    1.52
     Theatre
    1.47
     theatrical
    1.47
     Theater
    1.42
     театра
    1.41
    Theatre
    1.41
     teatro
    1.35
     théâtre
    1.35
    Theater
    1.33
    Activations Density 0.002%

    No Known Activations