© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2839
    Prev
    Next
    INDEX
    Explanations

    words or phrases regarding conflict or tension

    oai_token-act-pair · gemini-2.0-flash

    something developed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ثيق
    -0.51
    runOnUiThread
    -0.50
     CreateTagHelper
    -0.50
    ListTile
    -0.49
     cair
    -0.49
    DropTable
    -0.49
    createServer
    -0.48
     chiaro
    -0.48
    setupUi
    -0.47
     uParam
    -0.47
    POSITIVE LOGITS
     developed
    0.81
     unfolded
    0.76
     progressed
    0.73
     разви
    0.73
    developed
    0.71
     unfolds
    0.66
     gelişti
    0.65
     DEVELOP
    0.64
     develop
    0.63
     Developed
    0.63
    Activations Density 3.262%

    No Known Activations