© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1669
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to papers or figures.

    oai_token-act-pair · gemini-2.0-flash

    computing and legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Personendaten
    -0.72
    Enllaces
    -0.67
    apimachinery
    -0.60
    '));
    -0.60
    ddots
    -0.59
     "));
    -0.59
    `;
    -0.56
    "],
    -0.54
    ']));
    -0.54
    `,
    -0.54
    POSITIVE LOGITS
     TAMBIÉN
    0.69
     wikipagina
    0.56
     Elf
    0.54
    insten
    0.54
     initComponents
    0.54
    vidla
    0.52
     listener
    0.51
    abetta
    0.50
    WebControls
    0.50
    なった
    0.49
    Activations Density 12.332%

    No Known Activations