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. 13888
    Prev
    Next
    INDEX
    Explanations

    questions or conditional statements

    oai_token-act-pair · gemini-2.0-flash

    questions

    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
    بوابة
    -0.63
     fût
    -0.63
     eenige
    -0.58
     no
    -0.58
     nôtre
    -0.57
     présentés
    -0.57
     extérieures
    -0.56
     travaillons
    -0.56
     étoit
    -0.55
    WebVitals
    -0.54
    POSITIVE LOGITS
     there
    1.91
    there
    1.58
     THERE
    1.43
    There
    1.34
     There
    1.29
    THERE
    1.18
    theres
    0.75
     هناك
    0.74
     theres
    0.69
     lì
    0.66
    Activations Density 1.638%

    No Known Activations