© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15388
    Prev
    Next
    INDEX
    Explanations

    the definite article 'the' and other stop words, possibly as part of named entities or noun phrases.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oples
    -0.41
     S
    -0.41
    何より
    -0.38
     removed
    -0.38
    pygame
    -0.36
    iterran
    -0.36
     correctly
    -0.35
     apariencia
    -0.35
    umen
    -0.35
     won
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.97
     prevention
    0.96
     mitigation
    0.94
     retardation
    0.91
     AssemblyCulture
    0.90
     attenuation
    0.90
     maintenance
    0.89
     neutralization
    0.88
     suppression
    0.88
     relegation
    0.87
    Activations Density 7.494%

    No Known Activations