© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    oai_token-act-pair · gemini-2.0-flash

    terms related to fields and domains

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

    Physics simulations

    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
     CreateTagHelper
    -0.61
    drawSprites
    -0.59
    setVerticalGroup
    -0.59
     ostavi
    -0.59
    awtextra
    -0.57
     kaarangay
    -0.57
    IUrlHelper
    -0.55
    memoized
    -0.52
    цездатний
    -0.52
    AndEndTag
    -0.50
    POSITIVE LOGITS
     region
    0.55
     дописавши
    0.52
     tục
    0.50
     connected
    0.49
     ExecuteAsync
    0.49
     domain
    0.48
     Court
    0.47
    hika
    0.47
     environment
    0.47
    CONNECTED
    0.46
    Activations Density 4.619%

    No Known Activations