© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1529
    Prev
    Next
    INDEX
    Explanations

    Arabic script with associated escape sequences

    oai_token-act-pair · gemini-2.0-flash

    mixed language and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nahilalakip
    -0.57
    RRect
    -0.54
     tartalomajánló
    -0.48
    //});
    -0.47
    euvres
    -0.47
    országban
    -0.47
     RUE
    -0.47
     contem
    -0.46
    "});
    -0.46
    apunov
    -0.46
    POSITIVE LOGITS
     juridiques
    0.66
     vectorielles
    0.62
     fédé
    0.57
     financières
    0.56
     quelcon
    0.52
     extérieures
    0.52
     humaines
    0.51
    المصادر
    0.50
     humains
    0.50
     néglig
    0.49
    Activations Density 2.277%

    No Known Activations