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. 14194
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode equations and expressions

    oai_token-act-pair · gemini-2.0-flash

    mathematical/code notation

    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
    XmlAccessType
    -0.50
    کو
    -0.45
    styleable
    -0.44
    NameInMap
    -0.38
    ಳ
    -0.36
     di
    -0.36
    CELLANEOUS
    -0.36
    🤫
    -0.35
    but
    -0.35
    寇
    -0.35
    POSITIVE LOGITS
    ContentAsync
    0.78
    цездатний
    0.76
     AssemblyCulture
    0.73
    URLException
    0.73
    kuuta
    0.72
    fjspx
    0.71
     ModelExpression
    0.70
    tagHelperRunner
    0.69
    TargetApi
    0.69
    styleType
    0.68
    Activations Density 4.815%

    No Known Activations