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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8912
    Prev
    Next
    INDEX
    Explanations

    Javascript code, especially related to AngularJS (or Angular) controllers and directives, using the '$' symbol and keywords like 'scope', 'controller', 'directive', 'function', and 'app'.

    oai_token-act-pair · gemini-2.0-flash

    angular.js snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     utafitiHapana
    -0.94
    GEBURTSDATUM
    -0.85
    Tikang
    -0.81
     ―――――
    -0.81
     disambiguazione
    -0.76
    Clik
    -0.76
     متعلقه
    -0.75
    EndGlobalSection
    -0.75
     itſelf
    -0.74
     houſe
    -0.73
    POSITIVE LOGITS
     rapides
    0.60
     órganos
    0.54
     rápidas
    0.50
     ficam
    0.49
     classiques
    0.49
     supérieurs
    0.48
     rápidos
    0.47
     fidèles
    0.47
     salariés
    0.47
     intérieure
    0.46
    Activations Density 4.210%

    No Known Activations