© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11726
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations and some words that occur near them

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ंदीखरीदारी
    -0.67
     hjem
    -0.55
    AndroidJUnit
    -0.51
    shtml
    -0.50
    nościo
    -0.49
    caris
    -0.48
     Soler
    -0.48
    achite
    -0.48
     mø
    -0.47
     moat
    -0.47
    POSITIVE LOGITS
    AnchorStyles
    0.85
     pinulongan
    0.73
    AndEndTag
    0.65
    __':
    0.60
    forChild
    0.60
     Roskov
    0.59
    transQ
    0.59
     onOptions
    0.58
    bootstrapcdn
    0.58
    ️⃣
    0.58
    Activations Density 0.836%

    No Known Activations