© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10519
    Prev
    Next
    INDEX
    Explanations

    the keywords "var", "let", "const", periods, open parentheses, and the word "this", which are elements of javascript syntax

    oai_token-act-pair · gemini-2.0-flash

    Javascript variable declaration

    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
     prieten
    -0.49
     amoureux
    -0.49
     argint
    -0.47
     dår
    -0.46
     înal
    -0.45
     împreună
    -0.44
     anlaş
    -0.44
     nivelul
    -0.43
     scurt
    -0.43
     noastre
    -0.42
    POSITIVE LOGITS
    AccessorTable
    0.99
    tagHelperRunner
    0.96
    +#+#
    0.96
    IUrlHelper
    0.95
    DockStyle
    0.94
    sizeCache
    0.94
    jsxFileName
    0.87
     تضيفلها
    0.87
     Мексичка
    0.85
    ]--;
    0.85
    Activations Density 1.165%

    No Known Activations