© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4937
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds and reactions, especially those involving nitrates, oxides, and ammonia

    oai_token-act-pair · gemini-2.0-flash

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     travaillons
    -0.51
     copas
    -0.47
    Comté
    -0.47
    uasion
    -0.44
     Earth
    -0.44
     jongen
    -0.42
     earth
    -0.42
    copio
    -0.41
    ietf
    -0.41
     allow
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.90
    ########.
    0.84
    Personensuche
    0.77
    MemoryWarning
    0.74
     defaultstate
    0.72
    createClass
    0.68
    حوالہ
    0.67
     ivelany
    0.67
    awaiter
    0.66
    
    0.66
    Activations Density 2.385%

    No Known Activations