© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16324
    Prev
    Next
    INDEX
    Explanations

    mathematical equations, symbols, and notation.

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.55
    XPATH
    -0.48
     bag
    -0.48
     Bill
    -0.47
     "
    -0.46
    ↵↵
    -0.46
     A
    -0.46
     Bob
    -0.44
     Dar
    -0.43
     bags
    -0.43
    POSITIVE LOGITS
     مشين
    0.71
    IUrlHelper
    0.69
     enfans
    0.65
    rizona
    0.65
     creș
    0.61
     isComment
    0.60
    inerja
    0.60
     XNUMX
    0.60
     femininas
    0.60
     facilité
    0.59
    Activations Density 3.543%

    No Known Activations