© 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. 12340
    Prev
    Next
    INDEX
    Explanations

    the word "day"

    oai_token-act-pair · gemini-2.0-flash

    day

    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
     ModelExpression
    -0.52
     Ongoing
    -0.51
    ValueStyle
    -0.48
     suiv
    -0.48
    <bos>
    -0.47
    BlockPos
    -0.47
     للمعارف
    -0.46
    ItemCount
    -0.46
     kaynağından
    -0.46
    Ongoing
    -0.45
    POSITIVE LOGITS
    ients
    0.63
     pajama
    0.59
    verwijspagina
    0.58
    dicionado
    0.57
    commodation
    0.56
    IonicModule
    0.55
     Aladdin
    0.54
     entertainments
    0.54
    intenant
    0.54
    brities
    0.54
    Activations Density 6.496%

    No Known Activations