© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9961
    Prev
    Next
    INDEX
    Explanations

    language related to gender and equality issues

    oai_token-act-pair · gemini-2.0-flash

    women and gender

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     person
    -0.45
    info
    -0.44
     ca
    -0.44
    Syl
    -0.44
    ar
    -0.44
    wa
    -0.43
    f
    -0.43
    param
    -0.43
    нку
    -0.43
    シ
    -0.42
    POSITIVE LOGITS
    IndentedString
    1.09
     InputDecoration
    0.99
    Personensuche
    0.98
     للاسماء
    0.93
    InjectAttribute
    0.93
     Efq
    0.93
    expandindo
    0.93
    ThroughAttribute
    0.93
    TagMode
    0.92
    Geplaatst
    0.91
    Activations Density 12.784%

    No Known Activations