© 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. 14045
    Prev
    Next
    INDEX
    Explanations

    a variety of common words within sentences, without any particular theme

    oai_token-act-pair · gemini-2.0-flash

    "every" in different languages

    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
     all
    -0.95
    all
    -0.95
    All
    -0.94
     All
    -0.93
     allemaal
    -0.85
     semuanya
    -0.77
    ALL
    -0.77
     všetky
    -0.75
     všechny
    -0.72
     kaikki
    -0.72
    POSITIVE LOGITS
     every
    2.78
    every
    2.42
     Every
    2.19
    Every
    2.17
     ogni
    1.84
     setiap
    1.68
     EVERY
    1.66
     chaque
    1.59
     varje
    1.52
     cada
    1.49
    Activations Density 8.714%

    No Known Activations