© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11259
    Prev
    Next
    INDEX
    Explanations

    sentences where people are being described

    oai_token-act-pair · gemini-2.0-flash

    text snippets/quotes

    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
     ligiloj
    -0.62
     AspNetCore
    -0.59
     Roskov
    -0.56
    AutoField
    -0.55
    Demografie
    -0.54
     SIMBAD
    -0.52
     strokes
    -0.52
    Geplaatst
    -0.50
    PyErr
    -0.48
    ScopeManager
    -0.48
    POSITIVE LOGITS
    ...');
    0.63
    ()]);
    0.63
    interopRequire
    0.63
    ]));
    0.62
    */;
    0.61
    aughey
    0.61
    Tikang
    0.59
    '];
    0.58
    `;
    0.57
     AssemblyProduct
    0.57
    Activations Density 0.647%

    No Known Activations