© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9294
    Prev
    Next
    INDEX
    Explanations

    information and names of places and/or people and their claimed meanings

    oai_token-act-pair · gemini-2.0-flash

    lín

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.97
     createState
    -0.92
     Efq
    -0.91
     propOrder
    -0.90
     betweenstory
    -0.89
     Monfieur
    -0.89
     <>",
    -0.88
     fevere
    -0.86
     myſelf
    -0.85
    windowFixed
    -0.85
    POSITIVE LOGITS
    <eos>
    0.45
     [
    0.43
    rav
    0.43
     M
    0.43
    til
    0.43
    hu
    0.43
    mu
    0.42
    u
    0.42
    ero
    0.42
    cu
    0.42
    Activations Density 2.082%

    No Known Activations