© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13270
    Prev
    Next
    INDEX
    Explanations

    code syntax like method definitions and exception handling

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ContentAsync
    -1.01
     дописавши
    -1.00
    ValueStyle
    -0.95
     ostavi
    -0.93
    DockStyle
    -0.93
    expandindo
    -0.91
    AsUp
    -0.88
     Мексичка
    -0.88
     opérateur
    -0.87
     typelib
    -0.85
    POSITIVE LOGITS
     was
    0.69
     Was
    0.61
    Was
    0.58
     .
    0.54
    was
    0.52
    ↵
    0.50
     
    0.50
     k
    0.48
     ,
    0.46
     not
    0.46
    Activations Density 0.576%

    No Known Activations