© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11999
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "Royal [something] of"

    oai_token-act-pair · gemini-2.0-flash

    Royal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    migrationBuilder
    -0.88
    queryInterface
    -0.71
    OrBuilder
    -0.70
     PLWABN
    -0.67
    LabelTagHelper
    -0.66
    tığı
    -0.63
    AnchorStyles
    -0.63
     betweenstory
    -0.63
    RTGC
    -0.63
     []:
    -0.61
    POSITIVE LOGITS
    Tembelea
    0.52
     تانيه
    0.45
    entiary
    0.38
     Tub
    0.37
     跳转至
    0.37
    principalTable
    0.35
     ох
    0.34
    Tub
    0.32
     Dur
    0.32
    pylene
    0.32
    Activations Density 1.260%

    No Known Activations