© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3842
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to humanity and race

    oai_token-act-pair · gemini-2.0-flash

    human

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    addCriterion
    -0.63
    modelBuilder
    -0.48
    WaitGroup
    -0.48
     везе
    -0.46
    MemoryWarning
    -0.44
    ScopeManager
    -0.44
    TypedDataSet
    -0.43
     للمعارف
    -0.43
     pre
    -0.43
     pocos
    -0.42
    POSITIVE LOGITS
     human
    1.96
     humans
    1.90
    human
    1.80
    Human
    1.64
     HUMAN
    1.59
     Humans
    1.57
    humans
    1.55
     Human
    1.52
     humano
    1.50
    Humans
    1.48
    Activations Density 0.936%

    No Known Activations