© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12993
    Prev
    Next
    INDEX
    Explanations

    words and symbols representing components in React Javascript code

    oai_token-act-pair · gemini-2.0-flash

    uncommon 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Karp
    -0.67
    inhua
    -0.67
    Numerade
    -0.66
    CppMethod
    -0.66
    Ծանոթ
    -0.65
    FTFY
    -0.64
    rande
    -0.63
    AllAfrica
    -0.63
    enderror
    -0.63
    ifte
    -0.62
    POSITIVE LOGITS
     creș
    0.57
     myö
    0.50
     ameste
    0.50
     căr
    0.50
     oamen
    0.49
     luffy
    0.49
     îna
    0.48
     deschis
    0.47
     tecnici
    0.47
     essenziale
    0.46
    Activations Density 5.962%

    No Known Activations