© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3427
    Prev
    Next
    INDEX
    Explanations

    technical writing about data, numbers, or statistics

    oai_token-act-pair · gemini-2.0-flash

    say "number"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     number
    -1.88
    number
    -1.73
     numbers
    -1.66
    Number
    -1.62
     Number
    -1.59
     NUMBER
    -1.57
    NUMBER
    -1.51
     Numbers
    -1.45
     número
    -1.44
    numbers
    -1.41
    POSITIVE LOGITS
    lices
    0.48
    叉
    0.43
    upt
    0.43
    <bos>
    0.42
     o
    0.40
    ブリッド
    0.40
    ElementException
    0.39
     i
    0.39
     с
    0.39
    bits
    0.38
    Activations Density 4.061%

    No Known Activations