© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15124
    Prev
    Next
    INDEX
    Explanations

    code-like syntax, including braces, parentheses, and keywords like 'if', 'return', and 'void'

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    方が
    -0.57
    <>();
    -0.53
     tre
    -0.50
    RetentionPolicy
    -0.49
     sweet
    -0.48
    isert
    -0.47
    UTELY
    -0.47
     Ad
    -0.47
      (
    -0.47
    UnitTesting
    -0.47
    POSITIVE LOGITS
     חיצוניים
    0.63
     Himo
    0.62
     Audiodateien
    0.62
     Sensation
    0.59
     affitto
    0.59
     ThemeData
    0.58
     broek
    0.57
    unzel
    0.56
     staffel
    0.56
     feit
    0.55
    Activations Density 0.332%

    No Known Activations