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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9705
    Prev
    Next
    INDEX
    Explanations

    passages discussing operator precedence and prioritization

    oai_token-act-pair · gemini-2.0-flash

    prior

    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
     priority
    -1.76
     Priority
    -1.66
    priority
    -1.59
    Priority
    -1.54
     prioritized
    -1.43
     priorities
    -1.38
     prioritize
    -1.38
     prioriti
    -1.37
     prioritizing
    -1.31
     prioritise
    -1.30
    POSITIVE LOGITS
     prior
    1.78
    Prior
    1.59
     Prior
    1.55
    prior
    1.17
     PRIOR
    1.10
    PRIOR
    0.84
     previous
    0.73
    PreferredItem
    0.72
     earlier
    0.70
    nteral
    0.68
    Activations Density 1.756%

    No Known Activations