© 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. 11433
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages

    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_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
     inégal
    -0.42
     légère
    -0.38
     vänner
    -0.37
     supérieurs
    -0.37
     sû
    -0.37
    TagMode
    -0.36
     poë
    -0.36
     jambes
    -0.36
     ExecuteAsync
    -0.36
     mariée
    -0.35
    POSITIVE LOGITS
     Car
    0.77
    WebElementEntity
    0.72
     Point
    0.70
     "
    0.70
     came
    0.69
     Game
    0.69
     K
    0.68
     Pro
    0.68
     if
    0.68
     saw
    0.68
    Activations Density 30.782%

    No Known Activations