© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11965
    Prev
    Next
    INDEX
    Explanations

    references to wives, ladies, and noble women

    oai_token-act-pair · gemini-2.0-flash

    wife and mother

    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
     husband
    -0.92
     husbands
    -0.73
    husband
    -0.68
     father
    -0.67
     suaminya
    -0.66
     son
    -0.65
     Husband
    -0.63
    Husband
    -0.63
    婿
    -0.58
     him
    -0.57
    POSITIVE LOGITS
     wife
    1.31
     mother
    1.21
    wife
    1.12
    Wife
    1.09
     Wife
    1.09
    mother
    1.06
    Mother
    1.03
     Mother
    1.02
     wives
    1.01
     MOTHER
    0.99
    Activations Density 1.398%

    No Known Activations