© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10828
    Prev
    Next
    INDEX
    Explanations

    words in French related to internet-based communication or software

    oai_token-act-pair · gemini-2.0-flash

    Nationality

    np_max-act-logits · gemini-2.0-flash

    say "French"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     متعلقه
    -0.77
     Signalez
    -0.74
     pinulongan
    -0.64
    يميديا
    -0.63
     تانيه
    -0.62
     gynhyrchwyd
    -0.61
    AnimationsModule
    -0.60
    ConstraintMaker
    -0.59
    vedades
    -0.59
    Étymologie
    -0.57
    POSITIVE LOGITS
     chrétien
    1.22
     présidenti
    1.21
     chré
    1.20
     abstrait
    1.20
     asiatique
    1.19
     étranger
    1.19
     fédé
    1.17
     démocr
    1.17
     africain
    1.16
     préféré
    1.13
    Activations Density 9.232%

    No Known Activations