© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15615
    Prev
    Next
    INDEX
    Explanations

    code snippets, code-related terms, and XML or markup

    oai_token-act-pair · gemini-2.0-flash

    Class names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Tembelea
    -0.85
    oredCriteria
    -0.84
    انيف
    -0.80
    principalTable
    -0.79
    IsMutable
    -0.77
    .*")]
    -0.76
    EndGlobalSection
    -0.75
    httphttps
    -0.71
     ivelany
    -0.70
    RegistryLite
    -0.69
    POSITIVE LOGITS
    LoginActivity
    0.68
    jScrollPane
    0.57
    ProductService
    0.54
    HomeScreen
    0.53
    HomeComponent
    0.52
    AppRoutingModule
    0.50
    ServletContext
    0.47
    LoginPage
    0.46
    QMessageBox
    0.46
    MainActivity
    0.45
    Activations Density 5.351%

    No Known Activations