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. 14738
    Prev
    Next
    INDEX
    Explanations

    the word "from" and the phrase "from time to time."

    oai_token-act-pair · gemini-2.0-flash

    from

    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
     leçons
    -0.46
     informé
    -0.43
    XmlAccessType
    -0.40
     ніж
    -0.39
     livré
    -0.39
    masına
    -0.37
     rospy
    -0.37
     posé
    -0.36
    hlung
    -0.36
    acquisto
    -0.36
    POSITIVE LOGITS
     scratch
    1.07
     across
    0.89
     whence
    0.79
     EconPapers
    0.78
    scratch
    0.76
    across
    0.75
    RegressionTest
    0.74
    Scratch
    0.73
     متعلقه
    0.73
     abroad
    0.72
    Activations Density 1.690%

    No Known Activations