© 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. 13107
    Prev
    Next
    INDEX
    Explanations

    text snippets at the beginning or end of sentences or paragraphs in articles about health, cooking, planning, and education

    oai_token-act-pair · gemini-2.0-flash

    Health articles snippets

    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
    DockStyle
    -0.87
    modelBuilder
    -0.61
    InjectAttribute
    -0.58
    einander
    -0.52
    contentLoaded
    -0.50
     shade
    -0.49
    MessageTagHelper
    -0.49
    droje
    -0.47
    ريقة
    -0.46
    FormTagHelper
    -0.46
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.60
    DropColumn
    0.55
     חיצוניים
    0.53
     مشين
    0.52
    ++];
    0.52
     scattata
    0.51
     uuidv
    0.51
    heça
    0.51
     Souhaitez
    0.50
     croit
    0.49
    Activations Density 0.845%

    No Known Activations