© 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. 291
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to how frequently something occurs

    oai_token-act-pair · gemini-2.0-flash

    generalizations

    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
     jLabel
    -0.62
     Stoll
    -0.51
    AnimationsModule
    -0.50
    фан
    -0.48
    vad
    -0.48
    UserScript
    -0.48
     pleg
    -0.48
     „
    -0.47
    QMetaType
    -0.47
     Vitale
    -0.47
    POSITIVE LOGITS
     nearly
    0.84
    Nearly
    0.79
     Nearly
    0.78
    nearly
    0.74
     bijna
    0.73
     almost
    0.71
     near
    0.69
     resourceCulture
    0.68
    near
    0.68
    près
    0.68
    Activations Density 1.115%

    No Known Activations