© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11947
    Prev
    Next
    INDEX
    Explanations

    snippets of C# code, especially related to System.Windows.Forms and web services

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    outed
    -0.44
    き
    -0.41
     myself
    -0.41
     exc
    -0.39
     dép
    -0.39
    밖
    -0.39
    őd
    -0.39
    wami
    -0.38
    ורי
    -0.37
     geç
    -0.36
    POSITIVE LOGITS
    StoryboardSegue
    0.98
    хьтан
    0.91
     autorytatywna
    0.89
    NameInMap
    0.88
     विश्वसनीयता
    0.81
     مشين
    0.79
     estekak
    0.78
    Revenir
    0.78
     resourceCulture
    0.77
    twimg
    0.73
    Activations Density 0.454%

    No Known Activations