© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12848
    Prev
    Next
    INDEX
    Explanations

    words referring to family members, ancestry, and royal succession

    oai_token-act-pair · gemini-2.0-flash

    son

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     son
    -2.20
     Son
    -1.83
    Son
    -1.81
     sons
    -1.76
     daughter
    -1.68
    daughter
    -1.50
     SON
    -1.50
    son
    -1.46
     daughters
    -1.45
    Daughter
    -1.41
    POSITIVE LOGITS
    <?
    0.64
    Спољашње
    0.61
     himo
    0.57
    ագրություններ
    0.55
    ρασ
    0.53
    ThemeOverlay
    0.52
    TagMode
    0.52
     Befe
    0.51
     Abonnez
    0.51
    født
    0.51
    Activations Density 2.670%

    No Known Activations