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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6324
    Prev
    Next
    INDEX
    Explanations

    a mix of code, mathematical equations, and numerical digits

    oai_token-act-pair · gemini-2.0-flash

    references to locations or entities

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

    Code

    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
     
    -1.49
    ftagPool
    -0.60
     varandra
    -0.49
     hendes
    -0.47
     kvinna
    -0.47
    rdı
    -0.45
     colectiva
    -0.45
    ktır
    -0.44
     mijne
    -0.43
     jäsen
    -0.42
    POSITIVE LOGITS
     surla
    0.63
    
    0.62
    Obrázky
    0.62
     ویکی‌پدیای
    0.62
     وتسجيلات
    0.61
     发表于
    0.61
     Вікі
    0.60
     CURIAM
    0.57
     مشين
    0.57
    Lähteet
    0.56
    Activations Density 9.175%

    No Known Activations