© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    words or phrases connected to computer graphics, performance and frame rate

    oai_token-act-pair · gemini-2.0-flash

    Image/video processing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IntoConstraints
    -0.70
    Geplaatst
    -0.64
    elemField
    -0.63
    XmlAccessorType
    -0.63
     Abp
    -0.63
    istungen
    -0.62
     StatefulWidget
    -0.61
    AndEndTag
    -0.61
    QMetaType
    -0.60
     kasarigan
    -0.59
    POSITIVE LOGITS
     ant
    0.54
     anti
    0.51
     motion
    0.50
     downs
    0.50
     down
    0.48
    AtIndexPath
    0.47
     ups
    0.47
     resolution
    0.47
    ups
    0.46
    fahren
    0.45
    Activations Density 5.325%

    No Known Activations