© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10290
    Prev
    Next
    INDEX
    Explanations

    descriptions of fancy spaces like patios or decks, especially at night or including umbrellas

    oai_token-act-pair · gemini-2.0-flash

    under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    plona
    -0.58
    initComponents
    -0.54
    ctools
    -0.53
    fiche
    -0.53
    ariConfig
    -0.52
    ">—
    -0.52
    FormTagHelper
    -0.52
    AsUp
    -0.52
    orteur
    -0.51
     betweenstory
    -0.51
    POSITIVE LOGITS
     under
    1.42
    under
    1.17
     Under
    1.14
    Under
    1.14
     underneath
    1.10
     beneath
    1.09
     bajo
    1.04
     UNDER
    1.03
     sotto
    1.03
     sous
    0.92
    Activations Density 0.880%

    No Known Activations