© 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. 9353
    Prev
    Next
    INDEX
    Explanations

    chemistry terms like "alkyl", "aryl", "ides", "carbonyl", "esters"

    oai_token-act-pair · gemini-2.0-flash

    chemistry

    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
    исленность
    -0.79
     AssemblyCulture
    -0.66
     BrowserModule
    -0.65
    makeConstraints
    -0.60
    phosa
    -0.59
    expandindo
    -0.58
    ζει
    -0.57
    новниш
    -0.56
    hj
    -0.54
    blox
    -0.54
    POSITIVE LOGITS
    ysł
    0.50
    #+#
    0.50
    Risultati
    0.49
    olymers
    0.49
    CloseOperation
    0.48
    ModelForm
    0.48
    ysław
    0.47
    loride
    0.47
     JpaRepository
    0.47
    databinding
    0.47
    Activations Density 1.105%

    No Known Activations