© 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. 11708
    Prev
    Next
    INDEX
    Explanations

    language related to food policy and nutritional deficiencies

    oai_token-act-pair · gemini-2.0-flash

    context-related terms

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

    international development

    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
     ainfi
    -0.84
     Jefus
    -0.79
     preſent
    -0.78
     greateſt
    -0.78
     ſche
    -0.78
     quæ
    -0.75
     neceffary
    -0.75
     ſen
    -0.74
     cauſe
    -0.73
     laſt
    -0.72
    POSITIVE LOGITS
     useAppContext
    0.51
    PageContext
    0.50
     good
    0.50
    водитель
    0.50
     on
    0.50
    clusion
    0.49
    Geplaatst
    0.48
    Hentet
    0.48
     better
    0.47
    rías
    0.47
    Activations Density 1.043%

    No Known Activations