© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11559
    Prev
    Next
    INDEX
    Explanations

    snippets of code, especially related to object-oriented programming and accessing members of classes

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     كذلك
    -0.42
    ardı
    -0.41
     humanos
    -0.41
     oppure
    -0.40
     Others
    -0.40
    τας
    -0.40
     berikut
    -0.40
    办法
    -0.40
     secundarios
    -0.40
     altrimenti
    -0.39
    POSITIVE LOGITS
    <bos>
    1.77
    MigrationBuilder
    0.97
    IUrlHelper
    0.91
     المعيارى
    0.89
    Geplaatst
    0.85
    bootstrapcdn
    0.80
    ंदीखरीदारी
    0.78
    httphttps
    0.76
    expandindo
    0.72
    NamedQueries
    0.71
    Activations Density 0.516%

    No Known Activations