© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10788
    Prev
    Next
    INDEX
    Explanations

    words related to politics, especially words related to diplomatic incidents

    oai_token-act-pair · gemini-2.0-flash

    extraneous or unfamiliar terms

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

    diplomatic relations

    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
     actionMode
    -0.49
     '\\;'
    -0.48
    ="#"><
    -0.48
    StoreMessageInfo
    -0.48
    </thead>
    -0.46
    תיים
    -0.45
    aphone
    -0.44
    Pathway
    -0.44
    Metode
    -0.44
    Backbone
    -0.44
    POSITIVE LOGITS
    Portail
    0.70
     transfieras
    0.69
     SEDS
    0.62
    Демографія
    0.57
     transférez
    0.57
    FormBuilder
    0.54
     bouteilles
    0.54
    fjspx
    0.53
    kháu
    0.52
     Numerade
    0.50
    Activations Density 0.872%

    No Known Activations