© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6296
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be a collection of many different things, but is most strongly activated by subjects being acted upon in a negative manner, particularly if that acting involves a liquid or spray

    oai_token-act-pair · gemini-2.0-flash

    say prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    tagHelper
    -0.53
    seteq
    -0.47
    WIT
    -0.42
     ges
    -0.41
     attes
    -0.40
     Greeley
    -0.39
    úrg
    -0.39
    RequestHandler
    -0.39
    utnik
    -0.39
    WithEmail
    -0.38
    POSITIVE LOGITS
     into
    0.92
     onto
    0.85
    aarrggbb
    0.83
     تضيفلها
    0.80
     върху
    0.79
     betweenstory
    0.79
    SharedCtor
    0.77
     INTO
    0.76
     across
    0.75
    Into
    0.74
    Activations Density 2.307%

    No Known Activations