© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6423
    Prev
    Next
    INDEX
    Explanations

    mentions of regulatory agencies like the SEC, FDA, and others, along with related keywords.

    oai_token-act-pair · gemini-2.0-flash

    Government agencies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ChildScrollView
    -0.87
    StoreMessageInfo
    -0.84
    kháu
    -0.82
    tagHelperRunner
    -0.79
     NSCoder
    -0.78
    MethodManager
    -0.77
     שוליים
    -0.75
    脚注の使い方
    -0.72
     pinulongan
    -0.71
    CppCodeGen
    -0.71
    POSITIVE LOGITS
     cérami
    0.50
     solides
    0.44
     élect
    0.44
     fumée
    0.43
     béné
    0.43
     protezione
    0.39
     commerciales
    0.39
     soldadura
    0.38
     hornear
    0.38
     líquidos
    0.38
    Activations Density 1.508%

    No Known Activations