© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14824
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on sentences in German, checking for how many "modal verbs" such as "kann", "hätte", and "wollen" are used

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -2.70
    It
    -1.84
     It
    -1.80
    它
    -1.28
    it
    -1.21
     nó
    -1.20
    มัน
    -1.15
     آن
    -1.09
     它
    -1.06
     그것
    -0.95
    POSITIVE LOGITS
     es
    0.78
    -------
    0.63
     Es
    0.62
    Es
    0.62
     ddelweddau
    0.61
    MeasureSpec
    0.60
    DoubleQuotes
    0.58
     تضيفلها
    0.54
    yyj
    0.51
     AssemblyTitle
    0.51
    Activations Density 2.119%

    No Known Activations