© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2956
    Prev
    Next
    INDEX
    Explanations

    words related to children, babies, or newborns, especially in the context of discussing diapers and related experiences

    oai_token-act-pair · gemini-2.0-flash

    diapers

    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
    ular
    -0.45
     geldig
    -0.42
    gma
    -0.41
     $__
    -0.41
    stunde
    -0.41
     assur
    -0.41
    شن
    -0.40
     freddo
    -0.40
    ride
    -0.40
    serve
    -0.40
    POSITIVE LOGITS
     AssemblyProduct
    0.77
    хьтан
    0.73
    AndroidJUnit
    0.72
    styleType
    0.72
    LookAnd
    0.71
    featureID
    0.71
    
    0.68
    पया
    0.66
    GEBURTSDATUM
    0.66
    __':
    0.65
    Activations Density 1.104%

    No Known Activations