© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12491
    Prev
    Next
    INDEX
    Explanations

    words related to research contexts and methodologies

    oai_token-act-pair · gemini-2.0-flash

    vary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    diğinde
    -0.57
     além
    -0.48
    väg
    -0.48
    jsdelivr
    -0.47
    mıştır
    -0.45
    dafrika
    -0.44
    WebMethod
    -0.44
     vastaan
    -0.44
    gänger
    -0.43
    miştir
    -0.42
    POSITIVE LOGITS
     myſelf
    0.90
     itſelf
    0.83
     ſch
    0.79
     Monfieur
    0.78
     Efq
    0.74
     Majefty
    0.73
     raiſ
    0.73
     Shakspeare
    0.71
     faſt
    0.70
     themſelves
    0.66
    Activations Density 7.650%

    No Known Activations