© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    the word "gold" and related terms like "golden", "fields"

    oai_token-act-pair · gemini-2.0-flash

    gold

    np_max-act-logits · 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
     aught
    -0.58
    Rptr
    -0.52
     flesta
    -0.52
     chofe
    -0.51
    cism
    -0.50
    WebVitals
    -0.50
    numerusform
    -0.49
     faveur
    -0.48
     citer
    -0.48
     الميل
    -0.48
    POSITIVE LOGITS
    MLLoader
    0.54
    artifactId
    0.53
    انيف
    0.52
     незавершена
    0.52
    testng
    0.51
    تقاوى
    0.51
    cuda
    0.50
    parsedMessage
    0.48
    Демографія
    0.47
    EndInit
    0.47
    Activations Density 0.956%

    No Known Activations