© 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. 12450
    Prev
    Next
    INDEX
    Explanations

    news article publication formatting and common words within news headlines

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     BrowserModule
    -0.58
    principalColumn
    -0.52
    rzost
    -0.51
    <!--[
    -0.48
    __))
    -0.48
    AnchorStyles
    -0.45
    arResult
    -0.45
    ScopeManager
    -0.45
     الأخرى
    -0.44
     that
    -0.44
    POSITIVE LOGITS
     Jérusalem
    0.66
    StructEnd
    0.64
    AdapterFactory
    0.57
     estekak
    0.57
     Judea
    0.56
    RegressionTest
    0.55
    CppCodeGen
    0.54
    toral
    0.54
    ":[{
    0.52
    Photographer
    0.52
    Activations Density 5.953%

    No Known Activations