© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11568
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially those related to initializing, creating, showing, and updating.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    principalTable
    -1.05
    تقاوى
    -0.94
    évaluateur
    -0.88
    numerusform
    -0.82
     виправивши
    -0.81
     kaarangay
    -0.77
     estimés
    -0.76
    Tikang
    -0.75
    Personendaten
    -0.75
    NgModule
    -0.74
    POSITIVE LOGITS
    ullus
    0.46
      
    0.45
     inter
    0.44
     fonction
    0.44
     function
    0.44
     nag
    0.44
    UpdateCommand
    0.43
     năng
    0.43
    erry
    0.42
     Segu
    0.42
    Activations Density 9.883%

    No Known Activations