© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9515
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions, often involving the word "like."

    oai_token-act-pair · gemini-2.0-flash

    like or see

    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
    Negative Logits
    ondissement
    -0.56
    urium
    -0.56
    igene
    -0.54
    --){
    -0.53
    lifier
    -0.52
    laken
    -0.52
    ด์
    -0.50
    bsen
    -0.49
    ametro
    -0.49
    osex
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.64
     noqa
    0.62
    Revenir
    0.59
    ImageContext
    0.56
    onViewCreated
    0.56
    pushFollow
    0.55
    sizeCache
    0.53
     שוליים
    0.53
    __(/*!
    0.53
     termica
    0.52
    Activations Density 0.973%

    No Known Activations