© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14277
    Prev
    Next
    INDEX
    Explanations

    the word "equation" when it appears in a mathematical or physics context

    oai_token-act-pair · gemini-2.0-flash

    equation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AttributeSet
    -0.67
    NewUrlParser
    -0.67
    IntoConstraints
    -0.67
    ReusableCell
    -0.65
    HostException
    -0.64
     ſtate
    -0.62
    PagerAdapter
    -0.61
    Cyfeiriadau
    -0.60
    $__
    -0.59
    SourceChecksum
    -0.58
    POSITIVE LOGITS
    <bos>
    0.77
    μως
    0.67
    anmoins
    0.65
    []){
    0.60
    uttavia
    0.60
     the
    0.58
    ovo
    0.57
     '.')
    0.57
     ͡°)
    0.57
     a
    0.56
    Activations Density 0.591%

    No Known Activations