© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4263
    Prev
    Next
    INDEX
    Explanations

    articles and words that describe financial values or percentages

    oai_token-act-pair · gemini-2.0-flash

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     totals
    -0.55
     goals
    -0.49
     TOTAL
    -0.48
    ComponentName
    -0.48
     lifetime
    -0.48
    )}}{
    -0.47
     Total
    -0.47
     total
    -0.46
     Lifetime
    -0.46
     dimensions
    -0.45
    POSITIVE LOGITS
     متعلقه
    0.74
    mybatisplus
    0.65
    rifuge
    0.59
    CppCodeGen
    0.57
    出版年
    0.57
    AddHtmlAttribute
    0.57
    boks
    0.55
    Anas
    0.54
     disponibilités
    0.54
    Попис
    0.52
    Activations Density 6.978%

    No Known Activations