© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    terms from software development, particularly related to web development and asset management

    oai_token-act-pair · gemini-2.0-flash

    coding with rails and gulp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ſelf
    -0.72
    OGND
    -0.66
     quæ
    -0.66
     varandra
    -0.63
     préférence
    -0.62
     habet
    -0.62
    ſelves
    -0.62
     cherchés
    -0.60
    voorbeeld
    -0.60
     informacija
    -0.59
    POSITIVE LOGITS
    BASEPATH
    0.78
    routeProvider
    0.76
    SPATH
    0.71
    stateProvider
    0.68
    apimachinery
    0.67
    wpdb
    0.66
    djangoproject
    0.63
     EdgeInsets
    0.63
    WEBPACK
    0.62
     jspb
    0.61
    Activations Density 1.535%

    No Known Activations