© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3350
    Prev
    Next
    INDEX
    Explanations

    latex markup used in math papers

    oai_token-act-pair · gemini-2.0-flash

    ast

    np_max-act · gemini-2.0-flash

    asterisk

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     виправивши
    -0.61
    contentLoaded
    -0.60
    viewBox
    -0.59
    ReadAll
    -0.57
    sego
    -0.54
    )";
    -0.54
    UrlResolution
    -0.51
    StackSize
    -0.51
    ารถ
    -0.50
     оригіналу
    -0.49
    POSITIVE LOGITS
    <bos>
    0.69
    Дереккөздер
    0.62
     kasarigan
    0.60
     voks
    0.59
     Italij
    0.57
     lær
    0.57
     skolen
    0.56
    SwingConstants
    0.54
     hâte
    0.53
     vapeur
    0.53
    Activations Density 4.036%

    No Known Activations