© 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. 9827
    Prev
    Next
    INDEX
    Explanations

    the word "yesterday"

    oai_token-act-pair · gemini-2.0-flash

    yesterday

    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
     acknowledge
    -0.79
     ویکی‌پدیا
    -0.73
     acknowledged
    -0.72
     Acknowledge
    -0.71
     acknowledges
    -0.70
     acknowledging
    -0.66
     acknowled
    -0.64
    Acknowledge
    -0.61
     yesterday
    -0.61
    acknowled
    -0.60
    POSITIVE LOGITS
     judge
    0.66
    <?
    0.65
     lunch
    0.65
    ISODE
    0.63
    Rohy
    0.62
     &___
    0.60
    SerializedSize
    0.60
     judging
    0.56
    #+#
    0.54
     judges
    0.52
    Activations Density 0.753%

    No Known Activations