© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11763
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially HTML and XML tags, and related keywords like "class", "type", and "id".

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.69
    featureID
    -0.68
    RegisterType
    -0.67
    !*\
    -0.60
     autorytatywna
    -0.59
    SharedDtor
    -0.59
    Panamoan
    -0.58
    ArrowToggle
    -0.54
    GEBURTSDATUM
    -0.54
    LookAnd
    -0.50
    POSITIVE LOGITS
    новништво
    0.50
     QtGui
    0.50
    UIControlState
    0.49
    mappedBy
    0.45
     board
    0.44
     cref
    0.44
    RectangleBorder
    0.43
     оригіналу
    0.43
     hull
    0.42
     standing
    0.42
    Activations Density 2.842%

    No Known Activations