© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8964
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is narrating a story about themselves, especially from childhood, and/or stories involving sewing.

    oai_token-act-pair · gemini-2.0-flash

    family and children

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    -0.82
     wife
    -0.79
    husband
    -0.70
     suaminya
    -0.69
     husbands
    -0.69
     spouse
    -0.68
     Wife
    -0.66
    wife
    -0.65
     chồng
    -0.64
     wives
    -0.63
    POSITIVE LOGITS
     parents
    0.82
     school
    0.74
    oneofs
    0.71
     classmate
    0.71
    Parents
    0.69
     Parents
    0.68
    djangoproject
    0.67
     parent
    0.66
    تقاوى
    0.65
     schooling
    0.65
    Activations Density 2.770%

    No Known Activations