© 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. 8175
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation, particularly dollar signs surrounding single characters or expressions.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "provided"

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

    mathematical conditions and proofs

    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
    -0.82
    XmlAccessType
    -0.62
    orius
    -0.52
    vní
    -0.49
     Revenge
    -0.48
    mtp
    -0.48
    ishness
    -0.47
     friendship
    -0.47
     Femen
    -0.47
    ccount
    -0.46
    POSITIVE LOGITS
     provided
    0.70
    IUrlHelper
    0.61
    provided
    0.61
     @"/
    0.60
     imageNamed
    0.60
     PROVIDED
    0.59
     Provided
    0.57
     resourceCulture
    0.57
    rungsseite
    0.56
    StoreMessageInfo
    0.56
    Activations Density 9.645%

    No Known Activations