© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15604
    Prev
    Next
    INDEX
    Explanations

    C++ code, specifically include statements, namespace declarations, and the term "closely"

    oai_token-act-pair · gemini-2.0-flash

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     or
    -0.87
     new
    -0.67
     occur
    -0.62
     brand
    -0.58
     for
    -0.58
    occur
    -0.56
     occurring
    -0.56
     same
    -0.56
     last
    -0.55
     occurred
    -0.55
    POSITIVE LOGITS
    <bos>
    1.53
     Мексичка
    1.23
    ValueStyle
    1.16
    tagHelperRunner
    1.15
     Савезне
    1.14
    出版年
    1.12
     CreateTagHelper
    1.10
     صوتيه
    1.09
    ImageContext
    1.05
     مشين
    1.04
    Activations Density 0.390%

    No Known Activations