© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11762
    Prev
    Next
    INDEX
    Explanations

    the word sum in code or math texts

    oai_token-act-pair · gemini-2.0-flash

    sum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     sum
    -3.22
    sum
    -2.77
     Sum
    -2.56
    Sum
    -2.53
    SUM
    -2.03
     SUM
    -2.00
     sums
    -1.95
     Summe
    -1.75
     summed
    -1.68
     summing
    -1.67
    POSITIVE LOGITS
     Exacts
    0.71
    AccessorTable
    0.68
    oa̍t
    0.66
    SuppressLint
    0.62
    :+:
    0.61
     useStyles
    0.61
     Wikimédia
    0.60
    manship
    0.57
     %@",
    0.56
    וויק
    0.56
    Activations Density 0.416%

    No Known Activations