© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10455
    Prev
    Next
    INDEX
    Explanations

    miscellaneous seemingly unrelated terms, including office equipment, math symbols, place names, and words ending in "ing" in a specific context.

    oai_token-act-pair · gemini-2.0-flash

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Normdatei
    -0.98
     nakalista
    -0.96
     يتيمه
    -0.94
     مرئيه
    -0.92
     تضيفلها
    -0.91
    awtextra
    -0.91
    ThroughAttribute
    -0.90
     noDo
    -0.90
    ScopeManager
    -0.90
     ویکی‌پدیا
    -0.89
    POSITIVE LOGITS
     
    2.34
     
    0.64
     vastaan
    0.43
    <i>
    0.32
    육
    0.30
     kiin
    0.30
    (
    0.30
     edildi
    0.30
    flächen
    0.29
     válto
    0.28
    Activations Density 1.640%

    No Known Activations