© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10436
    Prev
    Next
    INDEX
    Explanations

    references to diversity and people

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     while
    -0.59
     whilst
    -0.58
     along
    -0.49
     (
    -0.45
     whereas
    -0.44
      
    -0.44
     mentre
    -0.42
    while
    -0.41
     throughout
    -0.41
     as
    -0.38
    POSITIVE LOGITS
     enfans
    0.95
     iſt
    0.88
     quæ
    0.88
     auffi
    0.88
     ſte
    0.85
     ſta
    0.85
     RSSSF
    0.81
     vœux
    0.80
     MUNDO
    0.80
     Jefus
    0.80
    Activations Density 3.780%

    No Known Activations