© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13904
    Prev
    Next
    INDEX
    Explanations

    negative numbers or sequences of numbers

    oai_token-act-pair · gemini-2.0-flash

    debugging, urls, and time stamps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     AssemblyCulture
    -1.16
    tagHelperRunner
    -0.97
     متعلقه
    -0.93
    تقاوى
    -0.92
    \{\\
    -0.92
    
    -0.92
     mergeFrom
    -0.91
     CreateTagHelper
    -0.90
    CppMethod
    -0.89
     propOrder
    -0.88
    POSITIVE LOGITS
    学
    0.43
     intptr
    0.43
    мести
    0.41
    duga
    0.41
    BindingSource
    0.39
     Sel
    0.39
    apt
    0.39
    PEI
    0.39
     sel
    0.38
    系
    0.38
    Activations Density 2.844%

    No Known Activations