© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15887
    Prev
    Next
    INDEX
    Explanations

    references to women, gender, equity, and their place in society.

    oai_token-act-pair · gemini-2.0-flash

    men and women

    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
     men
    -0.81
     Men
    -0.65
    Men
    -0.62
    men
    -0.58
     hommes
    -0.58
     MEN
    -0.56
    MEN
    -0.53
     Männer
    -0.49
     militaires
    -0.47
    norr
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.94
    DockStyle
    0.90
     الحره
    0.87
     للمعارف
    0.83
    BeginInit
    0.81
    клопе
    0.79
    出版年
    0.78
    KommentareTeilen
    0.74
     initComponents
    0.74
    setVerticalGroup
    0.73
    Activations Density 10.538%

    No Known Activations