© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal cases involving medical settings and correctional facilities, especially detention centers.

    oai_token-act-pair · gemini-2.0-flash

    references to detention centers

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

    center

    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
     resourceCulture
    -0.66
     ligiloj
    -0.63
    bewerken
    -0.63
    AnimationsModule
    -0.62
    بوابة
    -0.62
     ostavi
    -0.60
    parsedMessage
    -0.60
    NewUrlParser
    -0.59
    Personendaten
    -0.58
    addCriterion
    -0.56
    POSITIVE LOGITS
     center
    1.32
     centre
    1.12
    center
    1.07
     centers
    1.02
     Center
    0.97
    Center
    0.95
     CENTER
    0.94
    centers
    0.93
    CENTER
    0.92
    centre
    0.88
    Activations Density 1.486%

    No Known Activations