© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15305
    Prev
    Next
    INDEX
    Explanations

    code snippets and words related to website domains and programming

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Shakspeare
    -0.73
     Florentine
    -0.73
     Mep
    -0.71
     Yamato
    -0.70
     Haitian
    -0.70
     Cubans
    -0.69
     Siamese
    -0.68
     Beowulf
    -0.68
     Shaksp
    -0.68
     Fij
    -0.68
    POSITIVE LOGITS
     specchio
    0.60
     nemico
    0.56
     enfans
    0.56
     vectorielles
    0.54
     automatiques
    0.54
     présidenti
    0.53
     nemici
    0.51
     igenom
    0.51
     sguardo
    0.49
     sonno
    0.49
    Activations Density 0.215%

    No Known Activations