© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    words related to reflection or accurate representation

    oai_token-act-pair · gemini-2.0-flash

    accurately reflect

    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
    expandindo
    -0.43
    heden
    -0.39
    ViewImports
    -0.37
     sted
    -0.37
    (!__
    -0.35
    ôi
    -0.34
     Kün
    -0.34
    目
    -0.34
    SCROLL
    -0.33
    sweise
    -0.33
    POSITIVE LOGITS
     reflect
    2.05
     reflection
    2.03
     reflecting
    1.91
     reflects
    1.91
     reflected
    1.90
    reflect
    1.88
     Reflect
    1.84
     mirror
    1.72
     Reflection
    1.70
     reflections
    1.68
    Activations Density 1.230%

    No Known Activations