© 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. 2018
    Prev
    Next
    INDEX
    Explanations

    sentences that need to make a claim, but fall short

    oai_token-act-pair · gemini-2.0-flash

    programming terms and code snippets

    np_token-act-pair-logits · gpt-4o-mini
    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
     чтобы
    -1.58
     to
    -1.54
     để
    -1.39
     щоб
    -1.31
     upang
    -1.11
     чтоб
    -1.09
    Чтобы
    -1.06
     Чтобы
    -1.01
    来
    -0.98
    來
    -0.98
    POSITIVE LOGITS
    HtmlAttribute
    0.48
     ExecuteAsync
    0.47
     mouseY
    0.46
    __(/*!
    0.45
     ✭✭
    0.45
     atas
    0.41
    pegno
    0.40
    WireFormatLite
    0.40
     siitä
    0.40
     meille
    0.40
    Activations Density 6.970%

    No Known Activations