© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12388
    Prev
    Next
    INDEX
    Explanations

    words linked to the topic of jobs/work, particularly in traditionally male-dominated sectors as well as language around physical or mental ability.

    oai_token-act-pair · gemini-2.0-flash

    professions related to male-dominated fields

    np_token-act-pair-logits · gpt-4o-mini

    professions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    reportWebVitals
    -0.56
     AttributeSet
    -0.51
    AnimationsModule
    -0.47
     surla
    -0.44
    omination
    -0.42
    навли
    -0.40
    Respectfully
    -0.40
    cerely
    -0.40
    abestanden
    -0.40
    Hochspringen
    -0.39
    POSITIVE LOGITS
     engineers
    0.83
     salesmen
    0.78
     engineering
    0.77
     accountants
    0.75
     doctors
    0.75
     lawyers
    0.75
    scienti
    0.74
     Ingenie
    0.74
     Engineers
    0.72
     scientists
    0.70
    Activations Density 3.659%

    No Known Activations