© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3849
    Prev
    Next
    INDEX
    Explanations

    snippets of code, particularly related to JSON objects and arrays, file handling, and error handling

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming keywords

    np_token-act-pair-logits · gpt-4o-mini

    Code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Lähteet
    -0.51
    født
    -0.51
    ']):
    -0.46
    EndInit
    -0.43
     appelez
    -0.43
     platt
    -0.43
    SessionFactory
    -0.43
     $(\%)$
    -0.42
    obbies
    -0.42
    isBlank
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.82
    MigrationBuilder
    0.74
    bootstrapcdn
    0.66
     سكانية
    0.64
     XCTest
    0.62
     مرئيه
    0.59
    يكب
    0.57
     NSCoder
    0.56
     الاطلاع
    0.56
    setVerticalGroup
    0.56
    Activations Density 1.331%

    No Known Activations