© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14709
    Prev
    Next
    INDEX
    Explanations

    mentions of someone's spouse or family

    oai_token-act-pair · gemini-2.0-flash

    spouse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Mature
    -0.55
    IUrlHelper
    -0.54
    épa
    -0.54
    koh
    -0.54
    biť
    -0.53
     diterima
    -0.52
    bü
    -0.52
     îna
    -0.52
     entretien
    -0.51
    TemporalType
    -0.51
    POSITIVE LOGITS
     wife
    0.82
     Wife
    0.80
     wives
    0.75
    Wife
    0.75
     WIFE
    0.74
     spouses
    0.73
     Ehe
    0.70
     spouse
    0.67
    wife
    0.66
     married
    0.65
    Activations Density 1.065%

    No Known Activations