© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2913
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to cooking and eroding/wearing away

    oai_token-act-pair · gemini-2.0-flash

    cook and wear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     drink
    -0.98
     wear
    -0.93
     play
    -0.84
     eat
    -0.83
     swim
    -0.79
     pay
    -0.78
     sip
    -0.75
    drink
    -0.75
     wash
    -0.74
     cook
    -0.74
    POSITIVE LOGITS
    <bos>
    1.21
    yntaxException
    0.62
    はじめに
    0.59
     the
    0.58
    ρίζ
    0.57
     last
    0.53
     Reun
    0.52
     participle
    0.52
     Приступљено
    0.52
    řad
    0.51
    Activations Density 2.004%

    No Known Activations