© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12332
    Prev
    Next
    INDEX
    Explanations

    a broad set of function words such as prepositions, conjunctions, and determiners.

    oai_token-act-pair · gemini-2.0-flash

    specific foreign terms or technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    technical 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    none
    -0.62
    everywhere
    -0.62
     none
    -0.61
    Everywhere
    -0.55
    None
    -0.53
     everywhere
    -0.51
     überall
    -0.50
     partout
    -0.49
    neither
    -0.48
    these
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.94
    UrlResolution
    0.85
    tagHelperRunner
    0.77
    Salta
    0.75
    mybatisplus
    0.73
     חיצוניים
    0.71
    xase
    0.71
     resourceCulture
    0.70
     disambiguazione
    0.70
     تضيفلها
    0.69
    Activations Density 1.511%

    No Known Activations