© 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. 13562
    Prev
    Next
    INDEX
    Explanations

    terms related to physical and mental training or conditioning

    oai_token-act-pair · gemini-2.0-flash

    athletes or conditioning

    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
    Negative Logits
     upo
    -0.56
     getItemCount
    -0.44
    ipot
    -0.44
     aggiungere
    -0.44
     sensibilidad
    -0.43
    nología
    -0.42
     ricordare
    -0.42
    p
    -0.42
    ಾಗ
    -0.42
    Auto
    -0.42
    POSITIVE LOGITS
    AndroidJUnit
    0.63
    ArgumentParser
    0.63
    IntoConstraints
    0.63
     nahilalakip
    0.62
     athletes
    0.58
     gyms
    0.58
     athlete
    0.57
     protoimpl
    0.57
    didSet
    0.56
    رشف
    0.56
    Activations Density 0.548%

    No Known Activations