© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5412
    Prev
    Next
    INDEX
    Explanations

    open curly braces used in mathematical notation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    بوابة
    -0.55
    adaptiveStyles
    -0.54
    DeleteBehavior
    -0.50
    NewUrlParser
    -0.50
    zeptember
    -0.48
    Erstellt
    -0.47
    었습니다
    -0.46
    Przypisy
    -0.45
     houſe
    -0.45
     שוליים
    -0.45
    POSITIVE LOGITS
    rowse
    0.57
    اریخ
    0.52
    QMetaType
    0.51
    omitempty
    0.50
     StatefulWidget
    0.50
    spaceBetween
    0.50
    LEncoder
    0.49
    issances
    0.49
    ParallelGroup
    0.49
    țiune
    0.49
    Activations Density 0.046%

    No Known Activations