© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1892
    Prev
    Next
    INDEX
    Explanations

    keywords, variable declarations, and object properties in JavaScript and Typescript code

    oai_token-act-pair · gemini-2.0-flash

    Javascript variable declaration keywords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ])));
    -0.51
     său
    -0.47
     scienza
    -0.46
     uș
    -0.44
     comprendere
    -0.44
     rând
    -0.43
    '):
    -0.43
     scoperta
    -0.43
     calitate
    -0.43
     häng
    -0.43
    POSITIVE LOGITS
    úgó
    0.76
     ComVisible
    0.74
    npr
    0.68
    IndentedString
    0.66
     armature
    0.65
    Tapi
    0.65
    persion
    0.64
     onCreateView
    0.64
     url
    0.63
     body
    0.60
    Activations Density 0.739%

    No Known Activations