© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1812
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams, scores, and player debuts

    oai_token-act-pair · gemini-2.0-flash

    goal-related phrases or terms

    np_token-act-pair-logits · gpt-4o-mini

    scores and victories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.89
    دانشنامهٔ
    -0.81
     препратки
    -0.79
     disambiguazione
    -0.79
     jScrollPane
    -0.77
    UserScript
    -0.75
    MockBean
    -0.72
    principalColumn
    -0.71
    :✨
    -0.69
    extField
    -0.68
    POSITIVE LOGITS
     goal
    0.52
     levé
    0.48
    astă
    0.44
    ↘
    0.42
    openzeppelin
    0.42
     ну
    0.40
    ensaft
    0.39
     cauza
    0.39
    goal
    0.39
     Goal
    0.39
    Activations Density 0.654%

    No Known Activations