© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4147
    Prev
    Next
    INDEX
    Explanations

    words that appear to be related to math and science concepts

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     between
    -1.04
    between
    -0.97
     Between
    -0.94
     BETWEEN
    -0.93
    Between
    -0.93
     между
    -0.84
    BETWEEN
    -0.83
     zwischen
    -0.80
     betwixt
    -0.77
     pomiędzy
    -0.74
    POSITIVE LOGITS
    maten
    0.38
    DataPropertyName
    0.37
    joueurs
    0.36
     político
    0.36
     Dernière
    0.36
     WIRE
    0.36
    Giá
    0.36
    ![
    0.35
    Vía
    0.35
     Letra
    0.35
    Activations Density 6.250%

    No Known Activations