© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10233
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    code/math formulas

    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
    Negative Logits
     تضيفلها
    -0.67
    })));
    -0.62
     itſelf
    -0.60
    TypedDataSet
    -0.60
     ſeveral
    -0.59
     ModelRenderer
    -0.57
     AssemblyCompany
    -0.56
     δὲ
    -0.56
    RegressionTest
    -0.55
    tonode
    -0.54
    POSITIVE LOGITS
    
    0.57
    bersicht
    0.52
    requestCode
    0.49
     InputDecoration
    0.48
    مراجع
    0.47
    קישורים
    0.46
    afficheront
    0.46
    SPJ
    0.45
    PRNewswire
    0.45
    wirtschaft
    0.44
    Activations Density 1.025%

    No Known Activations