© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14002
    Prev
    Next
    INDEX
    Explanations

    words relevant to physics and spectra

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     spectrum
    -2.56
    spectrum
    -2.25
     Spectrum
    -2.08
    Spectrum
    -2.00
     spectra
    -1.84
     espectro
    -1.47
    spectra
    -1.45
     Spectra
    -1.34
     spectral
    -1.15
     спек
    -1.09
    POSITIVE LOGITS
    脚注の使い方
    0.81
    دانشنامهٔ
    0.78
    oa̍t
    0.76
    MarshalTo
    0.76
     AssemblyTitle
    0.76
    tagHelperRunner
    0.73
    #+#
    0.71
     Paglinawan
    0.70
    dataclass
    0.69
    posób
    0.69
    Activations Density 5.455%

    No Known Activations