© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14341
    Prev
    Next
    INDEX
    Explanations

    bracket characters used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    DockStyle
    -0.71
    windowFixed
    -0.57
    omonas
    -0.56
     Sciento
    -0.55
    ſelf
    -0.54
    ellschaft
    -0.54
     SIC
    -0.54
    Mania
    -0.54
     Carthag
    -0.54
     تضيفلها
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.54
     fermés
    0.52
    »).
    0.50
    Kaynakça
    0.49
     AssemblyCompany
    0.49
     schermata
    0.49
     exportación
    0.48
     keduanya
    0.48
     cintur
    0.48
    IUrlHelper
    0.47
    Activations Density 0.899%

    No Known Activations