© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6053
    Prev
    Next
    INDEX
    Explanations

    code snippets and math formulas with markup tags

    oai_token-act-pair · gemini-2.0-flash

    coding/math snippets

    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
     sum
    -2.38
     Sum
    -2.36
     SUM
    -2.27
    Sum
    -2.23
    sum
    -2.16
    SUM
    -2.14
     summation
    -1.99
     summary
    -1.98
     summarize
    -1.88
     Summary
    -1.85
    POSITIVE LOGITS
     فريبيس
    0.53
     flott
    0.51
    MENAFN
    0.50
    HtmlAttribute
    0.45
    DotNetBar
    0.43
    
    0.43
    íqu
    0.43
    kere
    0.42
     koch
    0.42
    Rüyada
    0.41
    Activations Density 3.465%

    No Known Activations