© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6787
    Prev
    Next
    INDEX
    Explanations

    the word "catch" in code or documentation

    oai_token-act-pair · gemini-2.0-flash

    catch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.27
     avoient
    -1.27
     Theſe
    -1.26
     ainfi
    -1.22
     mijne
    -1.21
     vectorielles
    -1.20
     aikaa
    -1.17
     quelcon
    -1.16
     étoit
    -1.16
     $_"
    -1.16
    POSITIVE LOGITS
    .
    0.81
    ...
    0.71
    _
    0.70
     fon
    0.69
    хо
    0.69
      
    0.69
    Ã
    0.66
    я
    0.65
     https
    0.65
     "
    0.65
    Activations Density 1.661%

    No Known Activations