© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11031
    Prev
    Next
    INDEX
    Explanations

    the word "Introduction" and section headings in technical documents

    oai_token-act-pair · gemini-2.0-flash

    Introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     lack
    -0.50
    porre
    -0.49
     qu
    -0.46
    lack
    -0.45
    eavor
    -0.44
    awtextra
    -0.43
    ţilor
    -0.43
    VIAF
    -0.42
    قليم
    -0.41
    qu
    -0.41
    POSITIVE LOGITS
     myſelf
    0.79
     Efq
    0.73
     Majefty
    0.73
     itſelf
    0.73
    ंदीखरीदारी
    0.72
     himſelf
    0.70
     Reſ
    0.70
     Monfieur
    0.68
     Jefus
    0.68
     greateſt
    0.68
    Activations Density 0.341%

    No Known Activations