© 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. 10815
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to elections and governments

    oai_token-act-pair · gemini-2.0-flash

    tokens related to airport and travel contexts

    np_token-act-pair-logits · gpt-4o-mini
    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
    RectangleBorder
    -0.95
    rinfo
    -0.84
    Ārējās
    -0.78
     ModelExpression
    -0.76
    enderror
    -0.75
    StructEnd
    -0.75
    AddTagHelper
    -0.74
     AssemblyVersion
    -0.74
    TintMode
    -0.73
     województwie
    -0.73
    POSITIVE LOGITS
     I
    0.47
    ji
    0.45
     &
    0.45
     cabeza
    0.44
    -
    0.43
    cientos
    0.42
     boca
    0.41
    纲
    0.40
    6
    0.39
    ype
    0.39
    Activations Density 0.364%

    No Known Activations