© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1954
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly in languages like Java or Python, possibly related to cloud services or web frameworks.

    oai_token-act-pair · gemini-2.0-flash

    code/data parsing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     فريبيس
    -0.86
     itſelf
    -0.84
     myſelf
    -0.78
     purpoſe
    -0.76
     themſelves
    -0.73
     ſhe
    -0.70
     AssemblyCulture
    -0.69
     reaſon
    -0.68
     unſ
    -0.66
     ſeveral
    -0.66
    POSITIVE LOGITS
    MigrationBuilder
    0.52
     Stuhl
    0.45
    enumi
    0.44
    co
    0.44
     OMITBAD
    0.44
    ğini
    0.44
    richTextPanel
    0.43
    ://
    0.42
     van
    0.42
    ومی
    0.42
    Activations Density 3.033%

    No Known Activations