© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 437
    Prev
    Next
    INDEX
    Explanations

    positive experiences and their immediate context.

    oai_token-act-pair · gemini-2.0-flash

    enjoy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     enjoy
    -1.89
     Enjoy
    -1.73
    enjoy
    -1.70
     enjoyed
    -1.68
    Enjoy
    -1.66
     enjoying
    -1.62
     enjoys
    -1.59
     ENJOY
    -1.58
    ENJOY
    -1.31
     enjoyment
    -1.30
    POSITIVE LOGITS
    GraphicsUnit
    0.56
    FetchType
    0.56
    BeginInit
    0.54
     Tasman
    0.52
    ['_
    0.52
    fony
    0.52
    λον
    0.52
    rxjs
    0.52
    (**
    0.50
    󠁢
    0.49
    Activations Density 5.479%

    No Known Activations