© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    company names with a "s" in the name, sometimes followed by the word "Edge"

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming keywords

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

    foreign words

    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
    BeginContext
    -0.63
     EconPapers
    -0.62
    مصادر
    -0.54
    ItemBackground
    -0.54
    >{@
    -0.49
     Baillargeon
    -0.49
    &
    -0.49
    ็จ
    -0.46
     krab
    -0.44
     lese
    -0.44
    POSITIVE LOGITS
     pinulongan
    0.74
    rmtree
    0.65
    DOCTYPE
    0.55
    حياته
    0.54
    Distribución
    0.54
    namentales
    0.53
     AppModule
    0.52
    روابط
    0.51
    odeficiency
    0.51
     Lumpur
    0.51
    Activations Density 3.561%

    No Known Activations