© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    references to research articles and medical measurements

    oai_token-act-pair · gemini-2.0-flash

    German names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ber
    -2.17
    Ber
    -2.14
    BER
    -2.08
     Ber
    -2.05
     ber
    -2.05
     BER
    -1.80
    berg
    -1.76
    BERG
    -1.75
    bergs
    -1.38
    bers
    -1.30
    POSITIVE LOGITS
    Bande
    0.48
    clonal
    0.46
     cystic
    0.44
     lampada
    0.43
     Mundial
    0.43
    Darius
    0.43
     divin
    0.42
     Amis
    0.42
    épar
    0.41
     sposob
    0.41
    Activations Density 0.624%

    No Known Activations