© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5253
    Prev
    Next
    INDEX
    Explanations

    words associated with academic or scientific writing, including words starting with "d" and lab settings

    oai_token-act-pair · 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
    InjectAttribute
    -0.77
    WebControls
    -0.60
    JspWriter
    -0.58
    interopRequire
    -0.58
    تقاوى
    -0.55
     Exactos
    -0.53
    expandindo
    -0.53
     testSet
    -0.53
     Chwiliwch
    -0.52
     few
    -0.52
    POSITIVE LOGITS
     toward
    0.65
    toward
    0.60
    lenül
    0.58
     into
    0.55
    irited
    0.54
    XmlAccessType
    0.54
    WithIOException
    0.54
    ronesia
    0.53
    setEditable
    0.53
    less
    0.53
    Activations Density 0.777%

    No Known Activations