© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13048
    Prev
    Next
    INDEX
    Explanations

    words related to data transfer from one source to another and HTML table elements

    oai_token-act-pair · gemini-2.0-flash

    Data/signal transmission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     pioggia
    -0.80
     nahilalakip
    -0.79
     Roskov
    -0.78
     ostavi
    -0.77
    Filmografie
    -0.77
     enfans
    -0.76
     lecz
    -0.74
    Diwedd
    -0.72
    SharedDtor
    -0.72
     forêts
    -0.71
    POSITIVE LOGITS
    люс
    0.54
    льта
    0.52
    レーション
    0.51
     ----------
    0.51
    fillType
    0.49
    tom
    0.49
     temps
    0.48
     setas
    0.48
    unse
    0.48
    الإنجليزية
    0.47
    Activations Density 1.140%

    No Known Activations