© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    snippets of text related to management, workplace dynamics, and legal employment context.

    oai_token-act-pair · gemini-2.0-flash

    employees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     customers
    -1.02
     Customers
    -1.01
    Customers
    -0.94
     Kunden
    -0.92
     client
    -0.92
     clients
    -0.89
     Clients
    -0.88
     customer
    -0.87
     clientes
    -0.86
     patient
    -0.85
    POSITIVE LOGITS
     employees
    1.48
     workers
    1.27
     staff
    1.23
    employees
    1.20
     Employees
    1.16
    Employees
    1.15
     EMPLOYEES
    1.13
     employee
    1.13
     staffers
    1.13
     employés
    1.09
    Activations Density 1.653%

    No Known Activations