© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11586
    Prev
    Next
    INDEX
    Explanations

    code statements including `if` statements, `#endif` preprocessor directives and some common code symbols such as curly braces and parentheses.

    oai_token-act-pair · gemini-2.0-flash

    endif

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    
    -0.73
    :✨
    -0.73
    +:+
    -0.67
    WebVitals
    -0.67
     protoimpl
    -0.66
    windowFixed
    -0.63
    UrlResolution
    -0.60
    AndEndTag
    -0.59
    adaptiveStyles
    -0.56
     ویکی‌پدی
    -0.55
    POSITIVE LOGITS
    UDAD
    0.52
    tamol
    0.52
     anteriore
    0.52
     samostat
    0.51
    GOTREF
    0.50
     Brasileira
    0.48
    InSection
    0.48
    danno
    0.48
    engertian
    0.48
     yarar
    0.48
    Activations Density 0.591%

    No Known Activations