© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6717
    Prev
    Next
    INDEX
    Explanations

    technical jargon from various fields

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and concepts

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

    Code or file paths

    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
     O
    -0.51
     W
    -0.51
     the
    -0.51
    。
    -0.49
     H
    -0.48
     is
    -0.48
    ).
    -0.46
     when
    -0.46
     U
    -0.46
     .
    -0.45
    POSITIVE LOGITS
     AssemblyProduct
    0.90
    MigrationBuilder
    0.88
    LookAnd
    0.88
     ModelExpression
    0.88
    WriteBarrier
    0.86
     betweenstory
    0.86
    UnusedPrivate
    0.83
    DrawerToggle
    0.82
    ViewFeatures
    0.77
    الحياه
    0.76
    Activations Density 9.972%

    No Known Activations