© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to democracy, celebration, and community engagement

    oai_token-act-pair · gemini-2.0-flash

    words related to celebration

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

    celebration

    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
    Not in Any Lists

    No Comments

    Negative Logits
     RSSSF
    -0.57
     contextLoads
    -0.55
     doInBackground
    -0.54
     occupe
    -0.48
     traseiro
    -0.47
    MigrationBuilder
    -0.47
     tø
    -0.47
    InSection
    -0.46
     EconPapers
    -0.46
    endcsname
    -0.46
    POSITIVE LOGITS
     celebration
    1.27
     celebrating
    1.24
     celebrate
    1.24
     promotion
    1.21
    celebr
    1.20
    celebrate
    1.11
     celebrates
    1.09
    promotion
    1.05
     Promotion
    1.05
     Celebration
    1.04
    Activations Density 2.851%

    No Known Activations