© 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. 7382
    Prev
    Next
    INDEX
    Explanations

    references to Disney and related media properties

    oai_token-act-pair · gemini-2.0-flash

    fairy tales and Disney

    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
    InputBorder
    -1.00
     resourceCulture
    -0.94
    oa̍t
    -0.93
    Tembelea
    -0.87
    ImageContext
    -0.85
    tagHelperRunner
    -0.84
    FailureListener
    -0.77
    URLException
    -0.75
    verwijspagina
    -0.75
     purpoſe
    -0.73
    POSITIVE LOGITS
     scene
    0.40
    Smar
    0.39
    wall
    0.38
     undetected
    0.37
     sc
    0.37
    الف
    0.36
    uccio
    0.36
     sugar
    0.35
    arma
    0.35
    össä
    0.34
    Activations Density 0.578%

    No Known Activations