© 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. 6462
    Prev
    Next
    INDEX
    Explanations

    lines of code in HTML and Javascript

    oai_token-act-pair · gemini-2.0-flash

    non-English text strings or code segments

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

    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_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
     cherchés
    -0.81
    LookAnd
    -0.73
    principalTable
    -0.68
    تقاوى
    -0.66
    
    -0.64
    apimachinery
    -0.61
     AssemblyTitle
    -0.59
    PropertyChanging
    -0.59
    Geplaatst
    -0.59
    WireFormatLite
    -0.59
    POSITIVE LOGITS
    帖最后由
    0.48
    NonQuery
    0.46
     taget
    0.42
    woor
    0.41
     volon
    0.38
    ╩
    0.38
     blanches
    0.38
    sour
    0.38
     sign
    0.36
     menghubungi
    0.36
    Activations Density 2.367%

    No Known Activations