© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5150
    Prev
    Next
    INDEX
    Explanations

    words with numbers and words related to scientific studies as well as legal proceedings and agreements

    oai_token-act-pair · gemini-2.0-flash

    therewith

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    存于互联网档案馆
    -0.63
     <<<<<<<<<<<<<<
    -0.51
     مشين
    -0.46
    initComponents
    -0.43
    ":[{
    -0.42
     prochains
    -0.42
    ⁡
    -0.41
    ;%
    -0.39
     aload
    -0.39
    dersfield
    -0.39
    POSITIVE LOGITS
    colgroup
    0.73
     becauſe
    0.70
     myſelf
    0.68
     themſelves
    0.68
    Tazama
    0.66
     doubtnut
    0.65
     AssemblyVersion
    0.64
     Monfieur
    0.63
     himſelf
    0.63
     Efq
    0.63
    Activations Density 10.312%

    No Known Activations