© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11476
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially years within bibliographical references and equations

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    CodeAttribute
    -0.58
    ArrowToggle
    -0.56
    sure
    -0.50
     Vikipedi
    -0.46
    spyOn
    -0.44
    HttpServlet
    -0.44
    bootstrapcdn
    -0.44
     sure
    -0.43
    Four
    -0.43
    umbi
    -0.43
    POSITIVE LOGITS
    0
    0.80
     betweenstory
    0.66
     zero
    0.63
    BarStyle
    0.57
     GreatSchools
    0.57
     Zero
    0.56
     cero
    0.55
    setCellStyle
    0.54
    SequentialGroup
    0.53
    ViewSet
    0.52
    Activations Density 2.484%

    No Known Activations