© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    a discussion of women's roles and policies, particularly relating to political administration, skilled labor, and discrimination

    oai_token-act-pair · gemini-2.0-flash

    gender roles in work

    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
     surla
    -0.84
    новништво
    -0.77
    setVerticalGroup
    -0.68
    Datuak
    -0.63
    EndInit
    -0.56
    <bos>
    -0.56
    matchCondition
    -0.54
    مصادر
    -0.51
    Équipe
    -0.51
    cshtml
    -0.50
    POSITIVE LOGITS
     men
    0.82
    хьтан
    0.71
     non
    0.60
     NSCoder
    0.57
    straight
    0.57
     low
    0.56
    InjectAttribute
    0.56
     straight
    0.55
     meningitis
    0.53
    quelize
    0.53
    Activations Density 4.293%

    No Known Activations