© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3927
    Prev
    Next
    INDEX
    Explanations

    the word "treatment" and other miscellaneous mathematical symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Diwedd
    -0.71
     للمعارف
    -0.66
    //
    -0.63
    rotum
    -0.63
    AndPassword
    -0.62
    ברס
    -0.61
    ContextHolder
    -0.59
     Trouver
    -0.58
     Morty
    -0.58
     Hummel
    -0.57
    POSITIVE LOGITS
    httphttps
    0.69
    ---*/
    0.55
    loten
    0.54
    ----</
    0.52
     eſ
    0.51
    titleMargin
    0.51
     ſaid
    0.48
    źdz
    0.48
    ,’”
    0.48
    Soorten
    0.47
    Activations Density 0.114%

    No Known Activations