© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7064
    Prev
    Next
    INDEX
    Explanations

    instances of auxiliary verbs linked by "to" and "and", suggesting the neuron detects a description of potential or required actions.

    oai_token-act-pair · gemini-2.0-flash

    function verbs related to processing and managing

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

    actions people can do

    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
     médicaux
    -0.80
     snippetHide
    -0.78
     normaux
    -0.70
     fermés
    -0.65
     mourut
    -0.65
     étoit
    -0.64
     feroit
    -0.64
     médicale
    -0.64
     heureuse
    -0.63
     juridiques
    -0.61
    POSITIVE LOGITS
    gypti
    0.58
     calculate
    0.55
    Autoritní
    0.54
     contribute
    0.53
     operate
    0.53
     jug
    0.52
     arrange
    0.52
     utilize
    0.50
    formKey
    0.50
     organize
    0.49
    Activations Density 2.954%

    No Known Activations