© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10225
    Prev
    Next
    INDEX
    Explanations

    code, specifically C++ and Java, including keywords, comments, and printing statements

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     مشين
    -0.88
    principalTable
    -0.77
     resourceCulture
    -0.68
     makeStyles
    -0.65
    存于互联网档案馆
    -0.64
    addContainerGap
    -0.63
    CppMethod
    -0.63
     initComponents
    -0.63
     }}$}
    -0.62
    exitRule
    -0.62
    POSITIVE LOGITS
     «
    0.56
    「
    0.51
    ***
    0.49
     「
    0.48
     "
    0.47
    Rec
    0.47
     “
    0.45
    {"
    0.45
    *******
    0.44
    **
    0.44
    Activations Density 3.708%

    No Known Activations