© 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. 9870
    Prev
    Next
    INDEX
    Explanations

    a variety of medical and food-related terms

    oai_token-act-pair · gemini-2.0-flash

    technical or scientific text

    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
     colors
    -1.67
     behavior
    -1.64
     color
    -1.64
    behavior
    -1.63
     labor
    -1.63
     Ее
    -1.59
     flavors
    -1.59
     Еще
    -1.57
     rumors
    -1.55
     favorite
    -1.54
    POSITIVE LOGITS
     defStyleAttr
    0.64
    甸
    0.63
    ciorys
    0.60
    脚注の使い方
    0.60
    fcntl
    0.59
    SuccessListener
    0.58
    jScrollPane
    0.57
     ChromeDriver
    0.56
     Audiodateien
    0.56
    ToListAsync
    0.56
    Activations Density 0.809%

    No Known Activations