© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6790
    Prev
    Next
    INDEX
    Explanations

    mentions of marital life involving possessions and work

    oai_token-act-pair · gemini-2.0-flash

    terms related to marriage or a spouse

    np_token-act-pair-logits · gpt-4o-mini

    wife

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -1.65
    husband
    -1.48
     husbands
    -1.38
     Husband
    -1.38
     suaminya
    -1.34
     marito
    -1.33
     marido
    -1.31
    Husband
    -1.29
     hubby
    -1.19
     esposo
    -1.10
    POSITIVE LOGITS
     wife
    0.80
     bride
    0.70
     wives
    0.66
    fjspx
    0.65
     אש
    0.65
     vrouw
    0.65
     Frau
    0.64
    wiſe
    0.63
     consultato
    0.62
     ż
    0.60
    Activations Density 1.064%

    No Known Activations