© 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. 12057
    Prev
    Next
    INDEX
    Explanations

    the letter J, often in the context of author names in citations

    oai_token-act-pair · gemini-2.0-flash

    J

    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
     J
    -0.91
    makeConstraints
    -0.75
    Дереккөздер
    -0.65
    derna
    -0.60
     centrif
    -0.60
    存于互联网档案馆
    -0.57
    Abitanti
    -0.56
    acos
    -0.56
     Cap
    -0.55
    slideUp
    -0.55
    POSITIVE LOGITS
    endphp
    0.78
    hawatir
    0.56
    wpi
    0.56
     craindre
    0.55
    BagLayout
    0.54
    jsonwebtoken
    0.54
     dourada
    0.52
     contemporanea
    0.51
     déco
    0.51
     KeyEvent
    0.50
    Activations Density 0.599%

    No Known Activations