© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3851
    Prev
    Next
    INDEX
    Explanations

    scientific text about RNA protein domains

    oai_token-act-pair · gemini-2.0-flash

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     domain
    -3.08
     Domain
    -2.84
    domain
    -2.83
    Domain
    -2.64
     domains
    -2.58
     DOMAIN
    -2.38
     Domains
    -2.38
    domains
    -2.14
    DOMAIN
    -2.13
    Domains
    -2.13
    POSITIVE LOGITS
    ंदीखरीदारी
    0.57
    сан
    0.52
    LikeLike
    0.51
    Fatalf
    0.49
    角
    0.46
    丁目
    0.45
     shake
    0.44
    fire
    0.44
    火
    0.44
     fire
    0.43
    Activations Density 1.130%

    No Known Activations