© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9733
    Prev
    Next
    INDEX
    Explanations

    the word "happen"

    oai_token-act-pair · gemini-2.0-flash

    happen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     happen
    -2.48
     happened
    -2.22
     happens
    -2.19
    happen
    -2.02
    happens
    -2.00
     happening
    -1.95
    happened
    -1.84
    <bos>
    -1.75
     Happens
    -1.75
     Happen
    -1.63
    POSITIVE LOGITS
    ரை
    0.59
    amid
    0.50
    foil
    0.47
    aima
    0.47
    nieder
    0.47
     MUNDO
    0.46
    uros
    0.46
    ophyta
    0.46
    perma
    0.45
     bla
    0.44
    Activations Density 1.013%

    No Known Activations