© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7364
    Prev
    Next
    INDEX
    Explanations

    text discussing Hersheys or chocolate chip cookies.

    oai_token-act-pair · gemini-2.0-flash

    bar

    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
    Negative Logits
    Autoritní
    -0.72
    LabelTagHelper
    -0.67
    modelBuilder
    -0.65
    IsContent
    -0.65
    出版年
    -0.65
     يتيمه
    -0.59
    fjspx
    -0.58
     незавершена
    -0.55
     thawed
    -0.54
     estekak
    -0.54
    POSITIVE LOGITS
     bar
    0.64
     Kit
    0.53
     anglès
    0.51
     barra
    0.50
     pinulongan
    0.49
    SuccessListener
    0.49
    Kit
    0.48
    ufort
    0.47
     FetchType
    0.47
    URLException
    0.47
    Activations Density 0.960%

    No Known Activations