© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7030
    Prev
    Next
    INDEX
    Explanations

    text from scientific documents involving measurements, chemical symbols, and numbers

    oai_token-act-pair · gemini-2.0-flash

    Scientific Research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    AndEndTag
    -0.74
     >=",
    -0.73
     Roskov
    -0.63
    titleMargin
    -0.63
    \{\\
    -0.62
    Personendaten
    -0.60
    出版年
    -0.60
     تضيفلها
    -0.56
    )];
    -0.54
    Diwedd
    -0.53
    POSITIVE LOGITS
    JspWriter
    0.52
     /*#__
    0.51
    MessageWindow
    0.51
     Organiser
    0.50
     Chaplin
    0.50
     Organizer
    0.47
    Organizer
    0.47
    ‰
    0.46
    Organ
    0.46
    tron
    0.46
    Activations Density 0.954%

    No Known Activations