© 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. 4496
    Prev
    Next
    INDEX
    Explanations

    words related to studies, analysis or research, no matter the focus

    oai_token-act-pair · gemini-2.0-flash

    Research and Technical articles

    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
     besar
    -0.60
     big
    -0.57
    Big
    -0.56
    SpringBootTest
    -0.56
    Huge
    -0.55
    InvalidProtocol
    -0.52
     Big
    -0.51
    大
    -0.47
    big
    -0.47
     Huge
    -0.46
    POSITIVE LOGITS
     propOrder
    0.78
     sauvage
    0.64
    цездатний
    0.62
    igshid
    0.60
    }`).
    0.59
     sauvages
    0.57
     tartalomajánló
    0.56
    Allez
    0.56
     competitive
    0.56
     delicado
    0.56
    Activations Density 23.416%

    No Known Activations