© 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. 4590
    Prev
    Next
    INDEX
    Explanations

    mentions of destiny, purpose and equality

    oai_token-act-pair · gemini-2.0-flash

    creation or purpose

    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
    contentLoaded
    -0.86
    featureID
    -0.79
    رشف
    -0.77
    expandindo
    -0.74
     المعيارى
    -0.73
    verwijspagina
    -0.69
    الحياه
    -0.66
    mybatisplus
    -0.63
    jsxFileName
    -0.62
    oredCriteria
    -0.60
    POSITIVE LOGITS
    VersionUID
    0.49
     Schia
    0.48
     Heights
    0.48
     caliber
    0.47
     suff
    0.47
    suff
    0.46
     sop
    0.46
    otheek
    0.46
     []).
    0.45
    copyOf
    0.45
    Activations Density 0.851%

    No Known Activations