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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 689
    Prev
    Next
    INDEX
    Explanations

    sport-related terms (mainly American football and basketball), and the articles "the," "a," and "an" that often precede them

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    DockStyle
    -0.60
     estimés
    -0.57
     Reverso
    -0.55
     mendes
    -0.52
    Numerology
    -0.52
    nocache
    -0.51
     виправивши
    -0.51
     حافظ
    -0.49
    gnore
    -0.49
    prüche
    -0.48
    POSITIVE LOGITS
    getMenuInflater
    0.56
    LLocation
    0.48
    enderror
    0.46
    illaries
    0.45
     Piran
    0.43
     ویکی‌پدیا
    0.43
    ếc
    0.43
    ătoare
    0.42
     Grecs
    0.42
     arşivlendi
    0.42
    Activations Density 3.938%

    No Known Activations