© 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. 767
    Prev
    Next
    INDEX
    Explanations

    words related to meals taken with family or in the community

    oai_token-act-pair · gemini-2.0-flash

    food and eating

    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
     drinking
    -0.80
     Drinking
    -0.77
    getDescriptor
    -0.66
     drinker
    -0.65
     kasarigan
    -0.65
     drinkers
    -0.64
     Drink
    -0.63
    drinking
    -0.63
    AsUp
    -0.63
     drink
    -0.62
    POSITIVE LOGITS
     tuck
    0.73
     nos
    0.59
     Infórmanos
    0.54
     tucked
    0.54
    ate
    0.48
     Autónoma
    0.46
     stuffed
    0.46
     rerum
    0.46
    Tuck
    0.45
     sav
    0.45
    Activations Density 2.927%

    No Known Activations