© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14900
    Prev
    Next
    INDEX
    Explanations

    technical and research-oriented words, particularly those related to scientific advancements and processes

    oai_token-act-pair · gemini-2.0-flash

    technological advancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     MainAxisSize
    -0.63
    Diweddarwch
    -0.63
    ReusableCell
    -0.63
    RenderAtEndOf
    -0.63
     Chwiliwch
    -0.61
    izielle
    -0.60
    はじめに
    -0.58
     ddelweddau
    -0.57
     Administrativna
    -0.56
    principalTable
    -0.55
    POSITIVE LOGITS
     Sloveniji
    0.55
     férfi
    0.53
    inerja
    0.52
     efektif
    0.50
     attivo
    0.50
     néz
    0.49
     borealis
    0.48
     sách
    0.48
    ',['
    0.48
    zugehen
    0.48
    Activations Density 33.766%

    No Known Activations