© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3829
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical research, treatments, and disease progression

    oai_token-act-pair · gemini-2.0-flash

    slowing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    seido
    -0.64
    INCREF
    -0.58
    EndInit
    -0.56
    QRST
    -0.56
    BeNil
    -0.55
    reactstrap
    -0.53
    ROIT
    -0.53
    oredCriteria
    -0.52
    DECREF
    -0.52
     otomatig
    -0.51
    POSITIVE LOGITS
     slowing
    1.01
     slows
    0.90
     slowed
    0.88
     ralenti
    0.85
     deceler
    0.81
     slowdown
    0.75
     Slow
    0.73
     delaying
    0.69
     deceleration
    0.69
     flatten
    0.68
    Activations Density 1.875%

    No Known Activations