© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12944
    Prev
    Next
    INDEX
    Explanations

    source code and html tags with a slight preference to finding the header tag and import statements from react.js

    oai_token-act-pair · gemini-2.0-flash

    HTML heading tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    </h3>
    -1.94
    </h6>
    -1.26
    </h5>
    -1.22
    </h4>
    -0.98
    </h2>
    -0.95
    )».
    -0.90
     }}$}
    -0.88
    );*/
    -0.87
    ;*/
    -0.87
    ();*/
    -0.79
    POSITIVE LOGITS
    RegressionTest
    0.87
    aarrggbb
    0.85
    NameInMap
    0.75
     Lightboxes
    0.71
     MainAxisSize
    0.71
    StreetMap
    0.69
    تقاوى
    0.69
     Normdatei
    0.69
    abestanden
    0.68
     HasFactory
    0.66
    Activations Density 2.127%

    No Known Activations