© 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. 14091
    Prev
    Next
    INDEX
    Explanations

    the word "spectrum" and "field", as used in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    spectrum

    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
    IntoConstraints
    -1.30
     disambiguazione
    -1.23
     виправивши
    -1.14
    rungsseite
    -1.08
    MessageTagHelper
    -1.07
    KURZBESCHREIBUNG
    -1.06
    :✨
    -1.03
    ConstraintMaker
    -1.02
    verwijspagina
    -1.02
    LogFactory
    -1.02
    POSITIVE LOGITS
     Je
    0.64
     a
    0.59
    ,
    0.56
    ฝ
    0.54
     later
    0.54
     limited
    0.53
    ściu
    0.52
    Thrown
    0.52
     earlier
    0.52
     First
    0.52
    Activations Density 1.722%

    No Known Activations