© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    words related to describing lines on graphs in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    lines, shapes, figures

    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
     setError
    -0.47
    usercontent
    -0.44
     cobre
    -0.42
    leben
    -0.41
    Rüyada
    -0.40
    ))$
    -0.39
    NameInMap
    -0.39
     Others
    -0.38
     cobertura
    -0.38
     linked
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.73
     /\.(
    0.69
    providedIn
    0.65
    IntoConstraints
    0.64
     Lightboxes
    0.63
     NSCoder
    0.63
     HttpNotFound
    0.63
    mtrl
    0.62
    FormTagHelper
    0.60
    tanleria
    0.60
    Activations Density 4.222%

    No Known Activations