© 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. 13236
    Prev
    Next
    INDEX
    Explanations

    short, common words in English and French text, especially in code-related contexts.

    oai_token-act-pair · gemini-2.0-flash

    "as" in other 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
    AndEndTag
    -0.61
    تقاوى
    -0.57
    NamedQueries
    -0.54
    रिक
    -0.54
     كومونز
    -0.52
     disambiguazione
    -0.51
     referenties
    -0.50
     חיצוניים
    -0.49
    +#+
    -0.49
    슷
    -0.48
    POSITIVE LOGITS
     as
    3.13
     sebagai
    1.45
    as
    1.41
    作为
    1.29
     как
    1.27
     као
    1.21
    作為
    1.15
    sebagai
    1.14
     ως
    1.12
     як
    1.11
    Activations Density 4.609%

    No Known Activations