© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2583
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to tasks, roles, work, and effort, frequently in the context of professional or skilled activities.

    oai_token-act-pair · gemini-2.0-flash

    work or tasks

    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
    tasks
    -0.63
     Tasks
    -0.60
    WriteAttribute
    -0.58
     laborious
    -0.56
    Tasks
    -0.56
     tasks
    -0.54
     labor
    -0.54
    المناصب
    -0.52
     làm
    -0.52
    libft
    -0.52
    POSITIVE LOGITS
    :✨
    0.71
    MemoryWarning
    0.56
     հղումներ
    0.55
    endphp
    0.54
     publiques
    0.52
    bibinfo
    0.51
     cancels
    0.50
     пей
    0.50
    typeparam
    0.49
     Chriftian
    0.49
    Activations Density 5.490%

    No Known Activations