Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 695
    Prev
    Next
    INDEX
    Explanations

    ingredients, units of measurement, and culinary verbs

    oai_token-act-pair · gemini-2.0-flash

    cooking recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AFX
    -0.50
     sür
    -0.45
    aksanaan
    -0.44
    middels
    -0.44
     Sterne
    -0.44
    nexo
    -0.43
     leopardo
    -0.43
    ‍
    -0.43
    {#
    -0.43
    NEED
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.77
     متعلقه
    0.65
    Билгалдахарш
    0.64
    RegressionTest
    0.61
    MemoryWarning
    0.60
    łaś
    0.59
    __*/
    0.59
     propOrder
    0.56
    Aiheesta
    0.56
    LLocation
    0.56
    Activations Density 4.153%

    No Known Activations