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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14266
    Prev
    Next
    INDEX
    Explanations

    the word "over" and the phrase "over the"

    oai_token-act-pair · gemini-2.0-flash

    Over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Alamos
    -0.53
     مشين
    -0.52
     étrangère
    -0.52
    CodeAttribute
    -0.51
    geführten
    -0.50
    RefNanny
    -0.50
     tartalomajánló
    -0.49
     wensen
    -0.45
    Ok
    -0.45
    taxia
    -0.45
    POSITIVE LOGITS
    Демографія
    0.60
    RegressionTest
    0.56
    makeConstraints
    0.53
    ;->
    0.53
    yorsunuz
    0.52
    Begriffsklä
    0.52
     Ouverture
    0.50
    MessageOf
    0.49
    Doctrine
    0.48
    CDCl
    0.47
    Activations Density 0.345%

    No Known Activations