© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9860
    Prev
    Next
    INDEX
    Explanations

    instances of the word "because" or similar words

    oai_token-act-pair · gemini-2.0-flash

    because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     because
    -1.87
    because
    -1.66
     porque
    -1.54
    Because
    -1.52
     BECAUSE
    -1.47
     Because
    -1.43
     becauſe
    -1.41
     потому
    -1.39
    porque
    -1.34
     Потому
    -1.31
    POSITIVE LOGITS
    ↵
    0.58
    </strong>
    0.54
    "
    0.50
     
    0.50
    '
    0.48
    <eos>
    0.47
    či
    0.46
    ırl
    0.45
    梭
    0.44
     "
    0.42
    Activations Density 0.701%

    No Known Activations