© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    information about U.S. television programs, especially music television programs, including broadcast dates and biographical information about hosts

    oai_token-act-pair · gemini-2.0-flash

    Television shows

    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
    RenderAtEndOf
    -0.94
     Chwiliwch
    -0.83
    ьаж
    -0.83
     defaultstate
    -0.75
    +#+#
    -0.75
    PerformLayout
    -0.74
    UnusedPrivate
    -0.73
    IUrlHelper
    -0.72
     مشين
    -0.70
    principalTable
    -0.69
    POSITIVE LOGITS
    edades
    0.47
     rock
    0.46
    ضايا
    0.43
    下来
    0.43
    kesh
    0.42
     club
    0.41
    வர்
    0.41
    жнему
    0.40
    akterysty
    0.40
    先代
    0.39
    Activations Density 1.226%

    No Known Activations