© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7492
    Prev
    Next
    INDEX
    Explanations

    mentions of Scottish councils, constituencies, and parliament, including years

    oai_token-act-pair · gemini-2.0-flash

    technical terms or entities

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

    UK politics and language

    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
     newBuilder
    -0.49
    AndEndTag
    -0.47
    interopRequire
    -0.46
    脚注の使い方
    -0.46
    ंदीखरीदारी
    -0.45
     fVar
    -0.45
    AutoresizingMask
    -0.44
    oneofs
    -0.44
    Зноскі
    -0.44
    ורים
    -0.43
    POSITIVE LOGITS
     Савезне
    0.65
    adto
    0.62
     GENERATED
    0.59
     EClass
    0.57
    MigrationBuilder
    0.57
    sizeCache
    0.56
     Seeder
    0.56
     ENGLAND
    0.56
     Waray
    0.54
    nologue
    0.54
    Activations Density 1.035%

    No Known Activations