© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16217
    Prev
    Next
    INDEX
    Explanations

    the phrase "customer service"

    oai_token-act-pair · gemini-2.0-flash

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     service
    -1.17
    service
    -1.11
    Service
    -0.77
     Service
    -0.73
     SERVICE
    -0.72
    xically
    -0.70
     servicio
    -0.68
    SERVICE
    -0.68
    ervice
    -0.67
     Потому
    -0.62
    POSITIVE LOGITS
     AssemblyTitle
    0.83
    GeneratedCode
    0.78
    ViewImports
    0.77
    Xna
    0.73
     GenerationType
    0.67
    /**
    0.66
    TypedDataSet
    0.61
     Sochi
    0.61
    PreAuthorize
    0.61
    bukkit
    0.60
    Activations Density 0.484%

    No Known Activations