© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2407
    Prev
    Next
    INDEX
    Explanations

    many different, lightly related things, including political terms, words about newspapers, a reference to Sherlock Holmes, and words about the stock market.

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
     copy
    -1.05
    copy
    -0.83
     Copy
    -0.80
    Copy
    -0.79
     COPY
    -0.75
     copied
    -0.63
     copiar
    -0.61
    COPY
    -0.60
     copying
    -0.56
     copies
    -0.55
    POSITIVE LOGITS
     ***!
    0.52
     NSCoder
    0.51
    TagMode
    0.51
    ]--;
    0.50
    Демографія
    0.50
    RetentionPolicy
    0.49
    Geplaatst
    0.49
     సౌకర్య
    0.48
    Portail
    0.48
     ویکی‌آمباردا
    0.47
    Activations Density 14.557%

    No Known Activations