© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    words ending in "ation" or having to do with light or radiation

    oai_token-act-pair · gemini-2.0-flash

    ations

    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
     CreateTagHelper
    -0.75
    tagHelperRunner
    -0.64
    يق
    -0.57
     dislocations
    -0.56
    unft
    -0.54
     dislocation
    -0.53
    ddots
    -0.52
    OUBLE
    -0.52
    PerformLayout
    -0.51
     interpretive
    -0.51
    POSITIVE LOGITS
    Autoritní
    0.75
    !("{}",
    0.61
    emit
    0.60
     émission
    0.60
     radiation
    0.59
     متعلقه
    0.58
     eman
    0.58
     beaming
    0.57
     InputDecoration
    0.57
     émissions
    0.56
    Activations Density 1.120%

    No Known Activations