© 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. 14736
    Prev
    Next
    INDEX
    Explanations

    LaTeX and mathematical symbols, especially those related to equations

    oai_token-act-pair · gemini-2.0-flash

    mk

    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
    الحياه
    -0.82
    EndContext
    -0.79
    المشاركات
    -0.78
    enumi
    -0.74
     pinulongan
    -0.68
     EconPapers
    -0.66
    apimachinery
    -0.62
     Majefty
    -0.62
     supplémentaires
    -0.61
    expandindo
    -0.60
    POSITIVE LOGITS
    PerformLayout
    0.49
    󠁿
    0.47
    发表于
    0.46
    portál
    0.46
    indari
    0.45
    StoryboardSegue
    0.45
    uncurkan
    0.44
     محفوظة
    0.44
    BIDDEN
    0.43
    ),),
    0.43
    Activations Density 36.946%

    No Known Activations