© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4431
    Prev
    Next
    INDEX
    Explanations

    words relevant to production and performance, such as plays, shows, and screenings

    oai_token-act-pair · gemini-2.0-flash

    say "py" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Perform
    -1.72
     performance
    -1.72
     performing
    -1.70
     perform
    -1.70
     Performance
    -1.68
    Performance
    -1.66
     performances
    -1.63
    perform
    -1.63
     performs
    -1.63
    Perform
    -1.63
    POSITIVE LOGITS
    sprozess
    0.59
    पया
    0.55
     py
    0.53
     casque
    0.48
    py
    0.48
     fièvre
    0.47
     sqlalchemy
    0.47
    idores
    0.47
    PYX
    0.46
    Py
    0.45
    Activations Density 0.591%

    No Known Activations