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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11659
    Prev
    Next
    INDEX
    Explanations

    strings of characters that commonly appear in website code, especially those related to image URLs, dates and objective-c code

    oai_token-act-pair · gemini-2.0-flash

    code-related elements and escape sequences

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

    Code/foreign languages

    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
    ագրություններ
    -0.72
    []>
    -0.68
    達
    -0.66
    ów
    -0.61
    lar
    -0.60
    ら
    -0.60
    々
    -0.58
    []
    -0.58
    らの
    -0.57
    AndEndTag
    -0.56
    POSITIVE LOGITS
    \{\\
    0.78
    MessageTagHelper
    0.66
     pinulongan
    0.60
    Demografia
    0.59
    esgue
    0.56
    出版年
    0.55
    paroles
    0.51
    INIS
    0.50
    ţia
    0.50
    ゴリー
    0.50
    Activations Density 0.390%

    No Known Activations