© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12374
    Prev
    Next
    INDEX
    Explanations

    Java or C# code syntax

    oai_token-act-pair · gemini-2.0-flash

    programming function calls and syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     up
    -0.59
    BeginContext
    -0.56
    up
    -0.55
     mort
    -0.52
    Up
    -0.50
    IndentedString
    -0.49
    prete
    -0.48
    expandindo
    -0.48
    zz
    -0.47
    tete
    -0.47
    POSITIVE LOGITS
    berdayakan
    0.69
    Cordialement
    0.63
     useRouter
    0.59
     vectorielle
    0.58
     للمعارف
    0.57
     auparavant
    0.56
     vérit
    0.55
     وتسجيلات
    0.55
     mengangg
    0.54
     ©️
    0.54
    Activations Density 0.259%

    No Known Activations