© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15306
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have" (ai) in French text

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    ai

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     st
    -0.46
     si
    -0.44
     du
    -0.43
    MethodManager
    -0.41
     pour
    -0.40
    بوابة
    -0.40
    Unione
    -0.39
     arcos
    -0.39
     ma
    -0.39
    siye
    -0.38
    POSITIVE LOGITS
     متعلقه
    0.93
    +#+#
    0.79
     Signalez
    0.71
     ModelExpression
    0.69
     referenties
    0.66
    ölkerung
    0.66
     intptr
    0.65
     AssemblyCulture
    0.64
     Philist
    0.64
    loem
    0.63
    Activations Density 0.797%

    No Known Activations