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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8809
    Prev
    Next
    INDEX
    Explanations

    anything that mentions both men and women

    oai_token-act-pair · gemini-2.0-flash

    Gender related topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Women
    -1.94
    Men
    -1.93
     females
    -1.91
     Females
    -1.90
     Women
    -1.90
     Men
    -1.88
    men
    -1.83
     men
    -1.82
    women
    -1.82
     WOMEN
    -1.80
    POSITIVE LOGITS
     الحره
    0.52
    日閲覧
    0.45
    новниш
    0.45
     ligiloj
    0.41
    dean
    0.37
    iega
    0.36
    Caster
    0.36
    ledem
    0.36
     Municipalidad
    0.35
    cooled
    0.35
    Activations Density 0.973%

    No Known Activations