© 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. 4352
    Prev
    Next
    INDEX
    Explanations

    C# code snippets, particularly related to namespaces, class creation, and referencing system libraries

    oai_token-act-pair · gemini-2.0-flash

    System

    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
     jäsen
    -0.88
     himſelf
    -0.85
     houſe
    -0.83
     whoſe
    -0.81
     näky
    -0.80
    <bos>
    -0.80
     myſelf
    -0.77
     themſelves
    -0.76
     rése
    -0.75
     againſt
    -0.75
    POSITIVE LOGITS
    Aiheesta
    0.71
    tagHelperRunner
    0.70
     مق
    0.60
    esgue
    0.59
    fromCharCode
    0.59
     Compound
    0.59
    ArgsConstructor
    0.59
    iburg
    0.58
     fre
    0.58
    paramref
    0.58
    Activations Density 0.263%

    No Known Activations