© 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. 844
    Prev
    Next
    INDEX
    Explanations

    references to lighthearted and potentially offensive interpersonal interactions around humor and food

    oai_token-act-pair · gemini-2.0-flash

    jokes and humor

    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
     joke
    -0.68
     funnier
    -0.60
     jokes
    -0.60
    InstrumentedTest
    -0.58
    Joke
    -0.58
    Архівовано
    -0.57
     protoimpl
    -0.57
     joked
    -0.56
     amusing
    -0.54
     funniest
    -0.54
    POSITIVE LOGITS
     inside
    0.70
    DeleteBehavior
    0.66
     RouterModule
    0.62
    inside
    0.60
    shadowOffset
    0.59
     Inside
    0.57
     StatelessWidget
    0.56
     cons
    0.55
    putstr
    0.54
     indisponible
    0.54
    Activations Density 1.897%

    No Known Activations