© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4221
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to governance, respect, and diplomacy

    oai_token-act-pair · gemini-2.0-flash

    Nonsensical words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <?
    -0.50
     actionPerformed
    -0.48
    Tembelea
    -0.47
     alfabe
    -0.47
    Życiorys
    -0.46
     ladder
    -0.46
    hup
    -0.44
     Вот
    -0.44
     podstaw
    -0.44
     valeurs
    -0.44
    POSITIVE LOGITS
     Numerade
    0.70
    featureID
    0.59
    sidemargin
    0.59
    tonsoft
    0.57
    لاعات
    0.55
    gestone
    0.53
     @}
    0.52
    courtesy
    0.52
    )_/¯
    0.52
    ViewImports
    0.51
    Activations Density 0.837%

    No Known Activations