© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    text related to staff support, especially in the context of work environments involving stress

    oai_token-act-pair · gemini-2.0-flash

    Customers/Clients

    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
     employees
    -1.16
     Employees
    -1.02
    Employees
    -1.01
    employees
    -0.93
     staff
    -0.93
     employee
    -0.92
     EMPLOYEES
    -0.90
     employés
    -0.86
     workers
    -0.85
    staff
    -0.83
    POSITIVE LOGITS
     customers
    1.00
     client
    0.99
     clients
    0.96
     Customers
    0.93
     Clients
    0.89
     Client
    0.86
    Customers
    0.86
    customers
    0.86
    client
    0.85
     customer
    0.85
    Activations Density 3.973%

    No Known Activations