© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5218
    Prev
    Next
    INDEX
    Explanations

    the term "vector bundle" and the letter "E" when used in math

    oai_token-act-pair · gemini-2.0-flash

    bundle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Bundle
    -2.11
     Bundle
    -1.84
     bundle
    -1.79
    bundle
    -1.66
     bundles
    -1.48
    bundles
    -1.24
     Bund
    -1.22
    UNDLE
    -1.20
     bund
    -1.18
     bundled
    -1.18
    POSITIVE LOGITS
    LabelTagHelper
    0.67
    errHandler
    0.66
    parsedMessage
    0.65
    BufferException
    0.64
    VersionUID
    0.63
    twimg
    0.60
    orado
    0.59
     Avis
    0.59
    ExecutionContext
    0.59
    endmodule
    0.59
    Activations Density 0.191%

    No Known Activations