© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14061
    Prev
    Next
    INDEX
    Explanations

    Java code snippets containing the word "Bean" or the keyword "final"

    oai_token-act-pair · gemini-2.0-flash

    Bean

    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
    Negative Logits
     final
    -0.74
     "
    -0.60
     fi
    -0.54
     specific
    -0.53
     inter
    -0.51
     di
    -0.50
     work
    -0.49
    -
    -0.49
    хани
    -0.49
     test
    -0.49
    POSITIVE LOGITS
     fermés
    1.02
     colorés
    1.00
     démocr
    0.97
     marquées
    0.93
     élas
    0.93
     élevées
    0.91
     longtemps
    0.90
     Efq
    0.88
     abandonné
    0.88
     récomp
    0.87
    Activations Density 1.235%

    No Known Activations