© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12001
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to patterns and change over time or within a system

    oai_token-act-pair · gemini-2.0-flash

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pattern
    -2.77
     Pattern
    -2.61
    pattern
    -2.50
    Pattern
    -2.48
     patterns
    -2.47
     PATTERN
    -2.30
     Patterns
    -2.28
    patterns
    -2.16
    Patterns
    -2.14
    PATTERN
    -2.03
    POSITIVE LOGITS
    tvguidetime
    0.75
    fjspx
    0.71
     '{@
    0.71
     للاسماء
    0.63
     EnglishChoose
    0.63
     EconPapers
    0.60
     étoit
    0.60
    úrese
    0.59
    ResponseWriter
    0.59
    IndentedString
    0.59
    Activations Density 8.936%

    No Known Activations