© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2746
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    Top results and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MainAxisSize
    -0.66
    elfth
    -0.58
    ynch
    -0.58
     nakalista
    -0.56
    robat
    -0.56
    7
    -0.55
    enumii
    -0.55
    >",
    -0.55
    катерина
    -0.54
    vif
    -0.54
    POSITIVE LOGITS
     ten
    0.77
    Ten
    0.75
     AssemblyCulture
    0.74
     Ten
    0.72
     five
    0.65
    five
    0.64
     TEN
    0.62
    ten
    0.61
     Five
    0.57
    Five
    0.56
    Activations Density 3.525%

    No Known Activations