© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4128
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to children and their health

    oai_token-act-pair · gemini-2.0-flash

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    child
    -0.78
     Child
    -0.76
     child
    -0.76
    ViewFeatures
    -0.75
    aarrggbb
    -0.75
    Child
    -0.74
     children
    -0.72
     Children
    -0.71
     nahilalakip
    -0.71
    Geplaatst
    -0.68
    POSITIVE LOGITS
    щадь
    0.49
    <bos>
    0.49
     lander
    0.49
     fondament
    0.48
    çamento
    0.47
    reactivex
    0.47
    OrWhiteSpace
    0.47
     brevemente
    0.47
    Präsident
    0.46
    .")]
    0.46
    Activations Density 24.164%

    No Known Activations