© 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. 15874
    Prev
    Next
    INDEX
    Explanations

    file extensions and file paths

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     LIST
    -0.48
    -0.45
    はじめに
    -0.43
     ویکی‌پدیا
    -0.43
    naf
    -0.43
    ListPage
    -0.41
     Ur
    -0.41
     list
    -0.41
    JA
    -0.41
     mạch
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    WarningLevel
    0.72
    CodedInputStream
    0.71
     initComponents
    0.71
     jScrollPane
    0.70
    ReusableCell
    0.69
     Monfieur
    0.68
     ArrayAdapter
    0.66
     ivelany
    0.65
     Efq
    0.65
    Activations Density 0.473%

    No Known Activations