© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2808
    Prev
    Next
    INDEX
    Explanations

    a variety of terms that are usually numerical values, and action verbs that suggest a process is being accomplished.

    oai_token-act-pair · gemini-2.0-flash

    numbers and completion

    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
    onViewCreated
    -0.87
    Demografía
    -0.63
     ExecuteAsync
    -0.58
    TextWatcher
    -0.57
     esternos
    -0.56
     للاسماء
    -0.55
    queryInterface
    -0.54
    
    -0.53
    Lähteet
    -0.53
     viewType
    -0.52
    POSITIVE LOGITS
    IsContent
    0.57
     emlé
    0.54
    writeFieldEnd
    0.54
     AssemblyProduct
    0.52
     Sob
    0.50
    DeleteBehavior
    0.50
    setMessage
    0.50
     BorderRadius
    0.49
    asteroide
    0.48
    oł
    0.48
    Activations Density 26.631%

    No Known Activations