© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    phrases expressing surprise or shock

    oai_token-act-pair · gemini-2.0-flash

    unexpected events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     surprise
    -2.78
    surprise
    -2.44
     surprises
    -2.36
    Surprise
    -2.36
     Surprise
    -2.33
     surprised
    -2.31
     surprising
    -2.30
     unexpected
    -2.16
     shock
    -2.02
     Überras
    -2.02
    POSITIVE LOGITS
    ArgsConstructor
    0.75
     ostavi
    0.54
    épend
    0.52
    olkien
    0.50
     pleas
    0.49
    abinieri
    0.46
    SpringBootTest
    0.46
     aapt
    0.45
    ỉnh
    0.45
     pleads
    0.45
    Activations Density 1.567%

    No Known Activations