© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1541
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions and catalysts

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

    np_token-act-pair-logits · gpt-4o-mini

    chemistry/catalysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kaarangay
    -0.43
     sofas
    -0.40
     CanadaChoose
    -0.39
     '\\;'
    -0.39
    AddWithValue
    -0.38
     obec
    -0.38
     tabl
    -0.38
     gmin
    -0.37
    期刊论文
    -0.37
    са
    -0.37
    POSITIVE LOGITS
    \{\\
    0.68
     onBind
    0.66
    ();)
    0.63
     Chwiliwch
    0.63
    Support
    0.63
    support
    0.62
    EndContext
    0.61
    upported
    0.60
    υμα
    0.59
     Support
    0.59
    Activations Density 2.337%

    No Known Activations