© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9550
    Prev
    Next
    INDEX
    Explanations

    a grab bag of programming code, acronyms, and words associated with political violence.

    oai_token-act-pair · gemini-2.0-flash

    URLs and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    CharStream
    -0.50
    Vision
    -0.49
    כשיו
    -0.48
    dibility
    -0.48
     draft
    -0.47
    Подготовка
    -0.47
    Fetch
    -0.46
     drafts
    -0.45
     whales
    -0.45
     hija
    -0.45
    POSITIVE LOGITS
    berdayakan
    0.66
    queryInterface
    0.64
    endphp
    0.63
     Wicidata
    0.58
    featureID
    0.57
    UnitTesting
    0.57
    bkz
    0.56
     Xunit
    0.55
    UserScript
    0.55
     autorytatywna
    0.54
    Activations Density 14.046%

    No Known Activations