© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    words related to the legal system, government, and international relations.

    oai_token-act-pair · gemini-2.0-flash

    adverbs or adverbial phrases

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

    legal documents

    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
    Negative Logits
    ölkerung
    -0.49
    FontOfSize
    -0.48
     насељу
    -0.44
    יוחד
    -0.44
    Климат
    -0.43
    CLUDE
    -0.42
    osomal
    -0.41
     Promise
    -0.40
    oudre
    -0.40
    unger
    -0.39
    POSITIVE LOGITS
     unilaterally
    1.05
    \{\\
    1.02
     respectfully
    1.00
     suddenly
    0.99
     always
    0.99
     confidently
    0.98
     successively
    0.97
     accidentally
    0.96
     somehow
    0.95
     systematically
    0.95
    Activations Density 1.658%

    No Known Activations