© 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. 9917
    Prev
    Next
    INDEX
    Explanations

    language related to baseball statistics and team names

    oai_token-act-pair · gemini-2.0-flash

    uncommon or specialized terms

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

    Baseball game summaries

    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
     المعيارى
    -0.58
    
    -0.56
     externi
    -0.56
    Демографія
    -0.56
     createSprite
    -0.55
    ніципалі
    -0.54
     kasarigan
    -0.53
     uParam
    -0.52
    ьаж
    -0.50
     فريبيس
    -0.50
    POSITIVE LOGITS
    ParallelGroup
    0.55
     autorytatywna
    0.50
     Мексичка
    0.50
    yentes
    0.50
     Tra
    0.48
     وتسجيلات
    0.48
    énéral
    0.48
     Inch
    0.48
    μερα
    0.47
    SourceChecksum
    0.47
    Activations Density 0.687%

    No Known Activations