© 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. 9469
    Prev
    Next
    INDEX
    Explanations

    the word "durable."

    oai_token-act-pair · gemini-2.0-flash

    durable

    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
    gl
    -0.63
     habet
    -0.55
     pensées
    -0.55
     Bolsa
    -0.55
    pe
    -0.53
    essen
    -0.53
    bu
    -0.52
    try
    -0.52
    at
    -0.52
     irse
    -0.51
    POSITIVE LOGITS
    <bos>
    1.35
     EconPapers
    1.33
    "):
    1.27
    
    1.25
    :✨
    1.23
    setVerticalGroup
    1.20
     Савезне
    1.20
    ")){
    1.17
     للمعارف
    1.16
    хьтан
    1.16
    Activations Density 1.446%

    No Known Activations