© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10972
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to biological processes, particularly those involving cells, genes, and medical research

    oai_token-act-pair · gemini-2.0-flash

    growth, trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    tableFuture
    -0.79
    原始内容存档于
    -0.74
     multer
    -0.70
     оригіналу
    -0.66
     للمعارف
    -0.65
     snippetHide
    -0.64
    óngase
    -0.61
     />';
    -0.60
    XmlType
    -0.59
     Belleville
    -0.57
    POSITIVE LOGITS
    <bos>
    0.54
    zyła
    0.52
    migrationBuilder
    0.50
    ament
    0.49
    oriam
    0.49
     detected
    0.48
    findpost
    0.48
    platin
    0.47
    vikle
    0.46
     prod
    0.46
    Activations Density 3.594%

    No Known Activations