© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5522
    Prev
    Next
    INDEX
    Explanations

    words related to mental and physical well-being, especially in a work environment

    oai_token-act-pair · gemini-2.0-flash

    stress

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     stress
    -2.83
     Stress
    -2.75
    Stress
    -2.69
    stress
    -2.56
     STRESS
    -2.52
     stresses
    -2.30
     stressed
    -2.14
     stressing
    -1.93
     stressful
    -1.90
     stres
    -1.90
    POSITIVE LOGITS
    HasForeignKey
    0.68
    Datuak
    0.62
     pinulongan
    0.60
     дописавши
    0.50
     ComVisible
    0.50
    endaftaran
    0.50
    TargetException
    0.48
     Reverso
    0.47
    st
    0.47
     hearth
    0.46
    Activations Density 2.820%

    No Known Activations