© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11266
    Prev
    Next
    INDEX
    Explanations

    months and some related words

    oai_token-act-pair · gemini-2.0-flash

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.67
     OFDb
    -0.62
    IntoConstraints
    -0.62
     saites
    -0.60
    Хьажоргаш
    -0.60
    TagMode
    -0.59
     autorytatywna
    -0.58
     Waray
    -0.58
     Italijanski
    -0.57
     initComponents
    -0.57
    POSITIVE LOGITS
    ,
    0.51
    canActivate
    0.50
     Polsek
    0.47
     estatales
    0.47
    Chham
    0.47
     MeV
    0.47
     déclar
    0.46
    šanās
    0.44
     ValidationError
    0.44
     darbu
    0.44
    Activations Density 3.592%

    No Known Activations