© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6878
    Prev
    Next
    INDEX
    Explanations

    mentions of opera, opera houses, and opera performers

    oai_token-act-pair · gemini-2.0-flash

    Opera and French music

    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
    phosa
    -0.44
     care
    -0.43
     оригіналу
    -0.42
    tick
    -0.41
    care
    -0.40
     Care
    -0.40
    Care
    -0.40
    rez
    -0.39
    quester
    -0.39
    cordova
    -0.39
    POSITIVE LOGITS
    AddTagHelper
    1.03
     MainAxisSize
    0.78
     تضيفلها
    0.66
    Personensuche
    0.65
    脚注の使い方
    0.64
     jouant
    0.60
     Мексичка
    0.59
     autorytatywna
    0.59
    abestanden
    0.59
    siąż
    0.57
    Activations Density 0.894%

    No Known Activations