© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11484
    Prev
    Next
    INDEX
    Explanations

    references to DNA and RNA, especially in medical research papers.

    oai_token-act-pair · gemini-2.0-flash

    DNA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     deck
    -0.98
    deck
    -0.84
     Deck
    -0.80
    Deck
    -0.77
     decks
    -0.75
     DECK
    -0.73
    decks
    -0.65
     Decks
    -0.60
    UrlResolution
    -0.54
     decking
    -0.52
    POSITIVE LOGITS
    <bos>
    1.05
     itſelf
    0.81
     quæ
    0.70
     raiſ
    0.70
    رشف
    0.69
     fufficient
    0.66
     становника
    0.66
    PINES
    0.66
     ſte
    0.65
     uſ
    0.65
    Activations Density 1.297%

    No Known Activations