© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5788
    Prev
    Next
    INDEX
    Explanations

    code structures associated with exception handling (try, catch)

    oai_token-act-pair · gemini-2.0-flash

    try/catch statements in code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     catches
    -0.79
     catching
    -0.70
     Catch
    -0.66
     catch
    -0.66
    Catch
    -0.65
    catching
    -0.63
     CATCH
    -0.61
     caught
    -0.60
    Catching
    -0.60
    CATCH
    -0.59
    POSITIVE LOGITS
    
    0.92
    errHandler
    0.82
    mybatisplus
    0.79
    CodedInputStream
    0.75
    JNIEnv
    0.71
    AndEndTag
    0.70
    NameInMap
    0.70
     MaterialApp
    0.69
    WebVitals
    0.69
    EndGlobalSection
    0.68
    Activations Density 1.040%

    No Known Activations