© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13692
    Prev
    Next
    INDEX
    Explanations

    words related to financial reports that mention delays caused by the COVID-19 pandemic

    oai_token-act-pair · gemini-2.0-flash

    cancellations

    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
    awtextra
    -0.75
     GenerationType
    -0.73
    omány
    -0.59
    GenerationType
    -0.57
    DotNetBar
    -0.57
    graphicx
    -0.57
    XmlAccessType
    -0.56
    
    -0.53
    BagConstraints
    -0.53
    TimeUnit
    -0.52
    POSITIVE LOGITS
     cancel
    0.95
    cancel
    0.86
     cancellation
    0.85
     cancelling
    0.84
     canceling
    0.83
     Cancel
    0.80
    Cancel
    0.76
     CANCEL
    0.73
     cancels
    0.73
     cancellations
    0.69
    Activations Density 1.344%

    No Known Activations