© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2857
    Prev
    Next
    INDEX
    Explanations

    words indicative of reaction, either physical actions or emotions shown by charachters either physical actions.

    oai_token-act-pair · gemini-2.0-flash

    facial expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NameInMap
    -0.74
     дописавши
    -0.68
     ſche
    -0.66
     AssemblyCulture
    -0.64
    PerformLayout
    -0.63
     ſch
    -0.62
     pleaſure
    -0.62
     Exacts
    -0.60
    webElementXpaths
    -0.60
     esternos
    -0.59
    POSITIVE LOGITS
     at
    0.59
     ami
    0.51
    InteropServices
    0.50
     Her
    0.47
     b
    0.46
    efois
    0.46
     surla
    0.46
     Kindly
    0.46
    alow
    0.46
    INATION
    0.46
    Activations Density 1.257%

    No Known Activations