© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15154
    Prev
    Next
    INDEX
    Explanations

    terms related to programming, particularly Javascript and ECMAScript

    oai_token-act-pair · gemini-2.0-flash

    non-English words or technical terms

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

    Spanish and Seville

    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
     '\\;'
    -0.50
     Baillargeon
    -0.48
    δο
    -0.48
     kos
    -0.47
    tagHelperRunner
    -0.46
    Nasc
    -0.43
    ض
    -0.43
    Zé
    -0.42
     Femen
    -0.41
     Godt
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.97
    Autoritní
    0.79
    出版年
    0.77
    PhysRevLett
    0.77
    GraphicsUnit
    0.76
    DockStyle
    0.73
    nologue
    0.70
     استنادى
    0.69
    脚注の使い方
    0.69
    はじめに
    0.65
    Activations Density 0.553%

    No Known Activations