© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6796
    Prev
    Next
    INDEX
    Explanations

    numbers, math symbols, and abbreviations that could be related to video frame rate and resolution, sometimes in the context of code

    oai_token-act-pair · gemini-2.0-flash

    video and project settings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     sound
    -1.00
    Sound
    -0.85
     Sound
    -0.84
    sound
    -0.83
     SOUND
    -0.79
     audio
    -0.77
     subtitles
    -0.71
    audio
    -0.71
    SOUND
    -0.71
     sounds
    -0.68
    POSITIVE LOGITS
    WebServlet
    0.64
     विश्वसनीयता
    0.55
    AccessorTable
    0.54
    hljs
    0.53
    脚注の使い方
    0.50
    AccessFile
    0.49
    jsx
    0.48
    forName
    0.48
     CreateTagHelper
    0.48
    illium
    0.48
    Activations Density 0.347%

    No Known Activations