© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11490
    Prev
    Next
    INDEX
    Explanations

    the fragment "ru" in various contexts, including chemical formulas, mathematical notation, and words

    oai_token-act-pair · gemini-2.0-flash

    ru

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ru
    -0.76
    ru
    -0.70
     
    -0.63
     potentially
    -0.59
      
    -0.58
     hopefully
    -0.55
     Ideally
    -0.53
     both
    -0.53
     I
    -0.53
    Ru
    -0.51
    POSITIVE LOGITS
     InputDecoration
    0.90
     DbContext
    0.88
     useRouter
    0.85
     snippetHide
    0.85
     Efq
    0.83
     useNavigate
    0.83
     useStyles
    0.83
    ngdoc
    0.81
    reszcie
    0.81
    zzleHttp
    0.80
    Activations Density 0.384%

    No Known Activations