© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2048
    Prev
    Next
    INDEX
    Explanations

    words related to babies and childbirth

    oai_token-act-pair · gemini-2.0-flash

    baby

    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
     baby
    -2.61
    baby
    -2.42
    Baby
    -2.39
     Baby
    -2.36
     BABY
    -2.14
    BABY
    -1.95
     babies
    -1.82
     Babies
    -1.59
     bébé
    -1.58
    babies
    -1.52
    POSITIVE LOGITS
    ThemeOverlay
    0.52
    esModule
    0.50
    ViewImports
    0.47
     exchangers
    0.44
    ListComponent
    0.44
     exchanger
    0.44
    chläge
    0.43
     adipo
    0.43
    chlag
    0.42
     moat
    0.42
    Activations Density 8.121%

    No Known Activations