© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially including titles of works and organizations

    oai_token-act-pair · gemini-2.0-flash

    General

    np_max-act · gemini-2.0-flash

    say "capitalized"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    skapet
    -0.55
    <eos>
    -0.53
    </strong>
    -0.50
    ess
    -0.50
    SharedDtor
    -0.47
     to
    -0.46
     Ro
    -0.45
    vores
    -0.45
     helpen
    -0.45
    </h2>
    -0.44
    POSITIVE LOGITS
     myſelf
    1.40
     pleaſure
    1.28
     purpoſe
    1.23
     Majefty
    1.17
    ſelf
    1.16
     reaſon
    1.16
     Houſe
    1.12
    ſelves
    1.12
     faſt
    1.09
     ſmall
    1.08
    Activations Density 4.297%

    No Known Activations