© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8402
    Prev
    Next
    INDEX
    Explanations

    references to wishes and dreaming, often in the context of a charitable foundation or fairy tale narrative

    oai_token-act-pair · gemini-2.0-flash

    wish

    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
    Negative Logits
    webElementXpaths
    -0.67
     Prü
    -0.53
     Saka
    -0.51
     Lla
    -0.51
    êmes
    -0.49
    calli
    -0.48
    onade
    -0.48
    Lla
    -0.47
    ernalia
    -0.47
     Prologue
    -0.46
    POSITIVE LOGITS
     wish
    1.53
     wishes
    1.47
     Wish
    1.38
    wish
    1.38
    Wish
    1.27
     wished
    1.24
     wishing
    1.20
     WISH
    1.20
     Wishes
    1.18
     deseos
    1.15
    Activations Density 0.555%

    No Known Activations