© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10626
    Prev
    Next
    INDEX
    Explanations

    terms related to family relationships, especially focusing on marital status and legitimacy of children

    oai_token-act-pair · gemini-2.0-flash

    legitimacy and paternity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     vermelhas
    -0.49
    Hochspringen
    -0.48
     voordeel
    -0.47
     Zeichen
    -0.47
    uação
    -0.46
     án
    -0.46
     shortness
    -0.45
     sanitarios
    -0.44
     estekak
    -0.44
     Tell
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.78
     ProtoMessage
    0.70
    FormTagHelper
    0.69
    Jereo
    0.63
     actionMode
    0.61
    تقاوى
    0.61
     ddelweddau
    0.60
    Portály
    0.60
     Paglinawan
    0.59
     referenties
    0.57
    Activations Density 0.741%

    No Known Activations