© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4433
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical systems and their status, for example load, operation, gear and position.

    oai_token-act-pair · gemini-2.0-flash

    engine operating conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    StoryboardSegue
    -0.61
     vPvB
    -0.60
     SEDS
    -0.50
    OrNil
    -0.49
     själva
    -0.49
    HasForeignKey
    -0.48
     löyty
    -0.48
    accompagnement
    -0.48
     ibland
    -0.48
    GenerationType
    -0.48
    POSITIVE LOGITS
    abatic
    0.60
    (!__
    0.56
    viewWillAppear
    0.52
    onResume
    0.51
     overnight
    0.50
     متعلقه
    0.50
    rrggbb
    0.49
    cinogen
    0.49
    AUTOR
    0.49
     للمعارف
    0.49
    Activations Density 2.660%

    No Known Activations