© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9813
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a variety of different things including code and multiple different languages, so it's hard to give a single explanation; it may be malfunctioning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     prevail
    -0.53
    ILY
    -0.52
    Portale
    -0.51
    lage
    -0.48
     detailing
    -0.48
    서는
    -0.48
     Er
    -0.47
    Er
    -0.47
     onlyOwner
    -0.47
    tis
    -0.47
    POSITIVE LOGITS
    IsContent
    0.76
     betweenstory
    0.72
    Hozzáférés
    0.72
    RTEX
    0.65
    ReusableCell
    0.64
     createState
    0.64
     مُعرِّف
    0.63
     CreateTagHelper
    0.62
    StoryboardSegue
    0.60
    ंदीखरीदारी
    0.59
    Activations Density 9.612%

    No Known Activations