© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1861
    Prev
    Next
    INDEX
    Explanations

    the articles "the," and possibly "a" and "an" within what appears to be news articles

    oai_token-act-pair · gemini-2.0-flash

    leading articles and tokens starting with a capital letter

    np_token-act-pair-logits · gpt-4o-mini

    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_21/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.21.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
     myſelf
    -1.50
     Monfieur
    -1.48
     Efq
    -1.37
     itſelf
    -1.33
     pleaſure
    -1.30
     Jefus
    -1.27
     ſche
    -1.26
     betweenstory
    -1.24
     iſt
    -1.23
     becauſe
    -1.23
    POSITIVE LOGITS
     
    0.84
     "
    0.74
     V
    0.67
     Z
    0.66
     S
    0.65
     “
    0.64
     p
    0.64
     B
    0.64
     J
    0.63
     G
    0.63
    Activations Density 5.740%

    No Known Activations