© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    product measurements and related words like "approximately", "size", or "wet"

    oai_token-act-pair · gemini-2.0-flash

    measurements and dimensions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    canestro
    -0.51
     yür
    -0.50
     кӀ
    -0.50
    lež
    -0.49
    biol
    -0.49
     Putnam
    -0.48
     Parkinson
    -0.47
     marié
    -0.47
    krank
    -0.47
     tombé
    -0.46
    POSITIVE LOGITS
    NameInMap
    0.82
     initComponents
    0.68
    mm
    0.61
    :+:
    0.60
    IBOutlet
    0.60
    oz
    0.57
    mens
    0.56
    UserScript
    0.54
     ExecuteAsync
    0.54
     ounce
    0.53
    Activations Density 4.371%

    No Known Activations