© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4359
    Prev
    Next
    INDEX
    Explanations

    code or formal writing that uses mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    computer science/mathematics

    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
     longest
    -0.68
    longest
    -0.66
    Longest
    -0.64
     shortest
    -0.60
    LocationManager
    -0.58
    cdnjs
    -0.58
     Longest
    -0.54
     largest
    -0.54
     best
    -0.54
    Shortest
    -0.52
    POSITIVE LOGITS
    Personensuche
    0.85
     MenuView
    0.77
    parsedMessage
    0.69
    脚注の使い方
    0.66
    XmlType
    0.63
    CrossRef
    0.59
    ItemBackground
    0.58
     vorbei
    0.57
    IRMED
    0.55
     elkaar
    0.55
    Activations Density 1.068%

    No Known Activations