© 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-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12939
    Prev
    Next
    INDEX
    Explanations

    words connected with the operation, people, and history of theatre and acting

    oai_token-act-pair · gemini-2.0-flash

    theatre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Teatro
    -0.69
     Theatre
    -0.66
    Theatre
    -0.64
    Theater
    -0.63
     theatre
    -0.63
     teatr
    -0.63
     theater
    -0.62
     teatro
    -0.61
    Théâtre
    -0.60
     Theater
    -0.60
    POSITIVE LOGITS
    ValueStyle
    0.91
     Waray
    0.80
    RenderAtEndOf
    0.77
     disambiguazione
    0.75
    PreferredItem
    0.68
    momix
    0.66
    Diwedd
    0.65
    WTS
    0.64
    WebVitals
    0.63
    InjectAttribute
    0.63
    Activations Density 11.025%

    No Known Activations