© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    the keyword "try" in code snippets indicating the start of a try-catch block.

    oai_token-act-pair · gemini-2.0-flash

    try

    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
     GenerationType
    -1.21
     CreateTagHelper
    -1.11
    sizeCache
    -1.05
     MainAxisSize
    -1.05
    expandindo
    -1.05
     AssemblyTitle
    -1.04
    EDEFAULT
    -1.04
     kasarigan
    -1.03
    ContentAsync
    -1.02
     pinulongan
    -1.02
    POSITIVE LOGITS
    ger
    0.42
    FA
    0.41
     FA
    0.40
    ve
    0.39
    bis
    0.39
    chá
    0.37
     Euch
    0.36
    ERA
    0.35
    ={[
    0.35
    ()
    0.34
    Activations Density 1.054%

    No Known Activations