© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10907
    Prev
    Next
    INDEX
    Explanations

    words related to royalty and servitude or performance due to the overlap of servants play and the words majesty and imperial.

    oai_token-act-pair · gemini-2.0-flash

    Royalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    luor
    -0.49
     Söhne
    -0.47
    armament
    -0.45
     manufacturer
    -0.44
     informer
    -0.42
    тьи
    -0.42
    Біографія
    -0.41
     duplo
    -0.40
    <tbody>
    -0.40
     tchèque
    -0.40
    POSITIVE LOGITS
    +#+
    0.95
     <>",
    0.91
    InjectAttribute
    0.84
     Wicidata
    0.81
     kaarangay
    0.80
     CreateTagHelper
    0.74
     pinulongan
    0.74
    GOTREF
    0.74
    twimg
    0.71
    UnsafeEnabled
    0.70
    Activations Density 0.279%

    No Known Activations