© 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. 3142
    Prev
    Next
    INDEX
    Explanations

    the prefix "inter-" and other prefixes or short words such as "tri-", "re-", "il-" , "officials", "r \ \ " and "than"

    oai_token-act-pair · gemini-2.0-flash

    inter

    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
    ↵↵
    -0.58
     "
    -0.57
    ://"
    -0.52
    zaamheid
    -0.51
     a
    -0.49
    ℗
    -0.47
     the
    -0.47
     ​​
    -0.47
    ppelin
    -0.47
    entista
    -0.47
    POSITIVE LOGITS
    <?
    0.78
     Sekund
    0.77
    BeginContext
    0.76
     potuto
    0.76
    teden
    0.76
    tableFuture
    0.75
    enderror
    0.74
     désol
    0.72
    omiast
    0.71
     riuscito
    0.71
    Activations Density 7.054%

    No Known Activations