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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5796
    Prev
    Next
    INDEX
    Explanations

    questions using different forms of "are."

    oai_token-act-pair · gemini-2.0-flash

    phrases beginning with "Are" and questions

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

    Are

    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
     it
    -1.71
    It
    -1.17
    它
    -1.10
     It
    -1.04
     оно
    -0.99
    มัน
    -0.85
    it
    -0.85
     nó
    -0.83
    它是
    -0.78
     آن
    -0.77
    POSITIVE LOGITS
    CloseOperation
    0.92
     you
    0.91
     they
    0.77
     these
    0.75
    RenderAtEndOf
    0.74
    ValueGenerated
    0.71
    ंदीखरीदारी
    0.69
     those
    0.69
    исленность
    0.68
     jsPsych
    0.63
    Activations Density 1.096%

    No Known Activations