© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2805
    Prev
    Next
    INDEX
    Explanations

    start or end of code blocks of Java or similar languages

    oai_token-act-pair · gemini-2.0-flash

    programming language structure and syntax

    np_token-act-pair-logits · gpt-4o-mini

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     arşivlendi
    -0.62
    msgSender
    -0.60
     دریافت‌شده
    -0.56
    bbene
    -0.54
     verkla
    -0.53
    awtextra
    -0.53
    horabuena
    -0.53
     hidupnya
    -0.50
    MFC
    -0.49
     Kerja
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.71
    UnknownFieldSet
    0.63
    MessageTagHelper
    0.58
    protoimpl
    0.57
     فريبيس
    0.57
    verwijspagina
    0.56
     noDo
    0.55
     متعلقه
    0.53
    mybatisplus
    0.52
    ItemLayout
    0.52
    Activations Density 0.915%

    No Known Activations