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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12647
    Prev
    Next
    INDEX
    Explanations

    snippets of computer code, especially Pascal and C++

    oai_token-act-pair · gemini-2.0-flash

    code punctuations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     kasarigan
    -0.72
    tvguidetime
    -0.68
    transQ
    -0.64
     ModelExpression
    -0.61
     StatefulWidget
    -0.61
     Италијани
    -0.59
    σθαι
    -0.58
    Personensuche
    -0.58
    RenderAtEndOf
    -0.57
    EndGlobalSection
    -0.56
    POSITIVE LOGITS
     Analyze
    0.55
     And
    0.55
    MemoryWarning
    0.53
     Or
    0.52
     Compile
    0.51
     couper
    0.51
     Organize
    0.51
    ManagedBean
    0.51
    licts
    0.50
    ticons
    0.50
    Activations Density 2.961%

    No Known Activations