© 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. 15292
    Prev
    Next
    INDEX
    Explanations

    comments and source code in Chinese and PHP, along with related terms such as "dictionary" and "compilation."

    oai_token-act-pair · gemini-2.0-flash

    Diverse information sources

    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
    ConstraintMaker
    -0.60
    RegressionTest
    -0.57
     виправивши
    -0.56
    <?
    -0.51
     estekak
    -0.49
    featureID
    -0.47
    endregion
    -0.45
    rippa
    -0.45
    CharStream
    -0.44
     minimum
    -0.43
    POSITIVE LOGITS
     voulais
    0.54
    的
    0.52
     生命周期
    0.52
     nemici
    0.51
    LEncoder
    0.50
     lesquelles
    0.49
    flavored
    0.49
    中的
    0.48
     '\\;'
    0.48
    ,  
    0.48
    Activations Density 1.487%

    No Known Activations