© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are related to scientific investigation, awards nominations, and government laws

    oai_token-act-pair · gemini-2.0-flash

    news and positive updates

    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
     AssemblyCulture
    -0.76
    .",
    -0.73
    JNIEnv
    -0.72
     виправивши
    -0.66
     voors
    -0.66
     protoimpl
    -0.66
     Sunt
    -0.65
    "]="
    -0.64
    !&
    -0.64
     الحره
    -0.63
    POSITIVE LOGITS
     for
    0.80
     FontWeight
    0.71
    _{-\
    0.71
     belf
    0.65
     offen
    0.61
     sirop
    0.61
    jeb
    0.61
     Alford
    0.60
     newVal
    0.60
    peng
    0.60
    Activations Density 4.265%

    No Known Activations