© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9513
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing quantities or scales, particularly numerical values

    oai_token-act-pair · gemini-2.0-flash

    articles and quantifiers

    np_token-act-pair-logits · gpt-4o-mini

    articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     ModelExpression
    -0.94
    InjectAttribute
    -0.93
    XtraReports
    -0.91
    TagMode
    -0.69
    WebElementEntity
    -0.68
     intptr
    -0.68
    LayoutPanel
    -0.67
     mergeFrom
    -0.67
     الرياضيه
    -0.67
    @[+][
    -0.67
    POSITIVE LOGITS
     a
    1.80
     an
    0.99
     einer
    0.65
     einem
    0.64
     een
    0.62
    a
    0.60
     एक
    0.60
     một
    0.60
     unui
    0.58
     eine
    0.58
    Activations Density 1.781%

    No Known Activations