© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7861
    Prev
    Next
    INDEX
    Explanations

    code snippets containing various operators and keywords from multiple programming languages.

    oai_token-act-pair · gemini-2.0-flash

    reading

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     EconPapers
    -0.54
    NameInMap
    -0.51
    исленность
    -0.49
    parsedMessage
    -0.47
     setTime
    -0.46
    kenalkan
    -0.43
    цезда
    -0.43
    حياتها
    -0.43
     Sid
    -0.42
    بوابة
    -0.42
    POSITIVE LOGITS
     read
    0.94
     reading
    0.93
     retrieving
    0.91
     retrieval
    0.90
     Read
    0.88
    read
    0.88
     READ
    0.85
     querying
    0.85
     reads
    0.84
    reads
    0.84
    Activations Density 3.560%

    No Known Activations