© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11726
    Prev
    Next
    INDEX
    Explanations

    the word "matter" often followed by "of" or "law" or "issue."

    oai_token-act-pair · gemini-2.0-flash

    matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     matter
    -3.08
    matter
    -2.69
     Matter
    -2.45
     MATTER
    -2.41
    Matter
    -2.36
     matters
    -2.13
    matters
    -1.80
     mattered
    -1.73
     Matters
    -1.71
     MATTERS
    -1.63
    POSITIVE LOGITS
     createState
    0.77
    BeginContext
    0.72
    TypedDataSet
    0.71
    tagHelperRunner
    0.69
     recevez
    0.68
     fidélité
    0.67
    :✨
    0.65
    LabelTagHelper
    0.65
    avoit
    0.64
     tramonto
    0.64
    Activations Density 3.272%

    No Known Activations