© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10298
    Prev
    Next
    INDEX
    Explanations

    words associated with conducting a research study

    oai_token-act-pair · gemini-2.0-flash

    case, data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.89
    RegressionTest
    -0.88
     CURIAM
    -0.83
     CreateTagHelper
    -0.76
     disambiguazione
    -0.76
    TestingModule
    -0.72
    GEBURTSDATUM
    -0.70
    tagHelperRunner
    -0.70
     ModelRenderer
    -0.68
     '\\;'
    -0.67
    POSITIVE LOGITS
     case
    0.69
     Case
    0.56
     cases
    0.54
    case
    0.53
    Case
    0.50
     caso
    0.49
     data
    0.47
     CASE
    0.46
    CASE
    0.46
    cases
    0.45
    Activations Density 1.250%

    No Known Activations