© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10108
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those in parentheses or related to currency

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     initComponents
    -0.80
     '\\;'
    -0.76
    rungsseite
    -0.75
    errHandler
    -0.74
     disambiguazione
    -0.71
    Autoritní
    -0.68
    oredCriteria
    -0.68
    исленность
    -0.66
    hassee
    -0.66
    featureID
    -0.65
    POSITIVE LOGITS
     Six
    0.48
    6
    0.48
    六
    0.47
     Sixth
    0.47
     六
    0.41
    2
    0.41
    geno
    0.41
    mann
    0.41
    бурга
    0.41
    7
    0.40
    Activations Density 1.381%

    No Known Activations