© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4758
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicles, specifically SUVs, their dimensions, and seating configurations

    oai_token-act-pair · gemini-2.0-flash

    Vehicle size and seating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     FontWeight
    -0.93
    ftagPool
    -0.81
    styleable
    -0.77
    ConverterFactory
    -0.77
    WebServlet
    -0.77
     onCancelled
    -0.76
     AssemblyTitle
    -0.73
    ביוגרפיה
    -0.73
     EconPapers
    -0.71
     createSlice
    -0.71
    POSITIVE LOGITS
     growth
    0.41
     demand
    0.41
     tiny
    0.39
    gouv
    0.37
    
    0.37
    go
    0.36
    init
    0.36
    has
    0.35
     go
    0.35
     ri
    0.35
    Activations Density 1.702%

    No Known Activations