© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15249
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C# and Java, involving caching, XML, and string manipulation

    oai_token-act-pair · gemini-2.0-flash

    code and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    PreferredItem
    -0.55
     Eras
    -0.54
     NSCoder
    -0.52
     виправивши
    -0.50
    vels
    -0.50
    eras
    -0.49
    internalType
    -0.49
     Majest
    -0.49
    出版年
    -0.49
     boroughs
    -0.47
    POSITIVE LOGITS
    saraba
    0.57
     &___
    0.56
     secondaires
    0.54
     efficaces
    0.54
    ParallelGroup
    0.53
    //
    0.52
     természetes
    0.51
    ℗
    0.51
     naturelles
    0.49
    #{
    0.49
    Activations Density 0.891%

    No Known Activations