© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12883
    Prev
    Next
    INDEX
    Explanations

    technical jargon from fields like computer programming, statistics, and electronics

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or class definitions

    np_token-act-pair-logits · gpt-4o-mini

    Code and software context

    np_max-act-logits · gemini-2.0-flash
    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
     vœux
    -0.78
     leçons
    -0.64
     êtres
    -0.63
     vérit
    -0.57
     prochaines
    -0.57
     âmes
    -0.57
     épaules
    -0.56
     preuves
    -0.54
     navires
    -0.54
    ipient
    -0.53
    POSITIVE LOGITS
    AnchorStyles
    0.71
     Offisielt
    0.68
     dafs
    0.65
    BeginContext
    0.64
    ſelves
    0.62
     perfons
    0.62
     dreamstime
    0.61
     fays
    0.60
     asics
    0.59
    ejs
    0.59
    Activations Density 24.838%

    No Known Activations