© 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. 15920
    Prev
    Next
    INDEX
    Explanations

    code in various programming languages, including HTML, Javascript, and Java.

    oai_token-act-pair · gemini-2.0-flash

    Code 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
     avoient
    -0.79
     feroit
    -0.75
     auroit
    -0.75
     étoient
    -0.73
     enfans
    -0.69
     pouvoit
    -0.65
     ainfi
    -0.64
     étoit
    -0.63
     prisonniers
    -0.60
     démocr
    -0.59
    POSITIVE LOGITS
    providedIn
    0.70
     BrowserModule
    0.68
    readAs
    0.67
    出版年
    0.65
    localctx
    0.65
     FetchType
    0.65
     IndexPath
    0.64
    createCanvas
    0.64
    ArrowToggle
    0.63
    webElementXpaths
    0.63
    Activations Density 10.314%

    No Known Activations