© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8422
    Prev
    Next
    INDEX
    Explanations

    the word "one" or numbers

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     one
    -0.88
     één
    -0.83
     одна
    -0.67
     один
    -0.67
     satu
    -0.66
     yksi
    -0.65
     одну
    -0.64
    One
    -0.63
     jednej
    -0.63
     ONE
    -0.62
    POSITIVE LOGITS
     thing
    0.81
    الحياه
    0.71
     person
    0.60
    awtextra
    0.58
    WebElementEntity
    0.57
    thing
    0.53
     item
    0.52
    !("{}",
    0.51
     thingy
    0.51
     place
    0.50
    Activations Density 1.156%

    No Known Activations