© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8182
    Prev
    Next
    INDEX
    Explanations

    words related to systems and processes, sometimes specifically technical or political systems

    oai_token-act-pair · gemini-2.0-flash

    Linear/binary concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    $_['
    -0.56
    πη
    -0.56
    LookAnd
    -0.53
    Autoritní
    -0.53
    #+#
    -0.53
    }{*}{
    -0.50
    FormTagHelper
    -0.48
     also
    -0.47
    avyzd
    -0.47
     limits
    -0.46
    POSITIVE LOGITS
    Aktualisiert
    0.53
     zatím
    0.50
    homonymie
    0.50
     وتسجيلات
    0.48
    μή
    0.44
    sidemargin
    0.44
     confusión
    0.44
     specchio
    0.44
    BagLayout
    0.44
     niitä
    0.44
    Activations Density 1.081%

    No Known Activations