© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9498
    Prev
    Next
    INDEX
    Explanations

    equations with math symbols

    oai_token-act-pair · gemini-2.0-flash

    \}_{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ImageContext
    -0.61
    InitVars
    -0.60
    rungsseite
    -0.60
     Bourgoin
    -0.60
    новниш
    -0.58
    afficheront
    -0.56
     kaarangay
    -0.56
    tonsoft
    -0.56
    RegressionTest
    -0.56
    anyahu
    -0.55
    POSITIVE LOGITS
    tagHelper
    0.64
    ftagPool
    0.56
     Lor
    0.52
     guilt
    0.50
    Lor
    0.48
     Realistic
    0.48
    ANCED
    0.48
     た
    0.48
    مصادر
    0.47
    Verdict
    0.47
    Activations Density 3.120%

    No Known Activations