© 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. 14951
    Prev
    Next
    INDEX
    Explanations

    code snippets or unusual word fragments

    oai_token-act-pair · gemini-2.0-flash

    code/technical language

    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
    Tembelea
    -0.69
    IntoConstraints
    -0.66
     laymen
    -0.58
     PIB
    -0.57
     existent
    -0.54
     Babylonian
    -0.52
     womanhood
    -0.52
     CommonModule
    -0.52
     Majority
    -0.51
    SFD
    -0.51
    POSITIVE LOGITS
    httphttps
    0.69
    uarga
    0.67
     Normdatei
    0.64
     cromo
    0.62
    NOPQRST
    0.61
    GeneratedCode
    0.60
     armon
    0.59
    XmlAccessType
    0.59
     sfor
    0.59
    InvalidProtocol
    0.57
    Activations Density 0.137%

    No Known Activations