© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15188
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with transportation, planning, development and infrastructure, particularly in an urban context.

    oai_token-act-pair · gemini-2.0-flash

    center

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    QMetaType
    -0.80
     propOrder
    -0.78
    PerformLayout
    -0.69
    providedIn
    -0.60
     protoimpl
    -0.59
    帖最后由
    -0.55
    ArrowToggle
    -0.54
    CppMethod
    -0.54
    memoized
    -0.54
    ReusableCell
    -0.54
    POSITIVE LOGITS
     center
    1.02
     Center
    0.93
    Center
    0.89
    CENTER
    0.88
    center
    0.87
     centro
    0.85
     centers
    0.82
     Centre
    0.82
     CENTER
    0.81
    centers
    0.78
    Activations Density 0.815%

    No Known Activations