© 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. 10556
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms, specifically related to sending data and setting output in audio/video applications

    oai_token-act-pair · gemini-2.0-flash

    Code output/sending

    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
    PerSecond
    -0.97
    Retries
    -0.97
    FullPath
    -0.94
    DirPath
    -0.94
    Elems
    -0.94
    ToSend
    -0.91
    ForUser
    -0.89
    InProgress
    -0.89
    InOrder
    -0.88
    EndTime
    -0.87
    POSITIVE LOGITS
    ImageContext
    1.45
    DockStyle
    1.40
     myſelf
    1.38
     Monfieur
    1.32
    IsMutable
    1.31
     auroit
    1.27
    IsContent
    1.26
     ProtoMessage
    1.25
     uſed
    1.21
     étoit
    1.20
    Activations Density 0.912%

    No Known Activations