© 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. 5338
    Prev
    Next
    INDEX
    Explanations

    sentences describing miniatures painting techniques

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms and functions

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

    art and design description

    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
     facie
    -0.52
    templateUrl
    -0.50
    šče
    -0.45
     internacionais
    -0.43
     teşekkür
    -0.42
    исленность
    -0.42
     finitely
    -0.42
     öz
    -0.41
     Ripper
    -0.41
     planta
    -0.40
    POSITIVE LOGITS
    writeFieldEnd
    1.01
    InjectAttribute
    0.89
    RenderAtEndOf
    0.88
    URLException
    0.84
     sumpay
    0.84
    tagHelperRunner
    0.81
     gynhyrchwyd
    0.80
    Tembelea
    0.79
    MLLoader
    0.77
    queryInterface
    0.76
    Activations Density 3.251%

    No Known Activations