© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13323
    Prev
    Next
    INDEX
    Explanations

    words ending in "ation" or "ment" that are related to scientific concepts

    oai_token-act-pair · gemini-2.0-flash

    ation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ation
    -1.36
    ness
    -1.29
    ment
    -1.16
    ization
    -1.11
    ity
    -1.09
    fication
    -1.08
    isation
    -1.02
    NESS
    -0.97
    ism
    -0.96
    ATION
    -0.90
    POSITIVE LOGITS
     giudi
    0.71
     croit
    0.66
     peindre
    0.63
     esempi
    0.63
     déploy
    0.62
     supérieures
    0.62
     solares
    0.61
     completos
    0.61
     InputDecoration
    0.60
     faciles
    0.60
    Activations Density 2.005%

    No Known Activations