© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13945
    Prev
    Next
    INDEX
    Explanations

    words that have to do with the concept of variety

    oai_token-act-pair · gemini-2.0-flash

    diversity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    */}
    -0.57
    hatenablog
    -0.57
     Cassini
    -0.56
     Jove
    -0.54
    ंदीखरीदारी
    -0.53
     INSEE
    -0.53
     aught
    -0.53
     AHL
    -0.52
     correctes
    -0.52
     Diwali
    -0.52
    POSITIVE LOGITS
    서는
    0.63
     giao
    0.60
     ioutil
    0.60
    TestBed
    0.59
     Weis
    0.58
    áctenos
    0.58
     nor
    0.56
     ufficio
    0.55
    anias
    0.55
    BagLayout
    0.55
    Activations Density 1.149%

    No Known Activations