© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16272
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating extremes or large amounts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.65
    SpringBootTest
    -0.59
    angelo
    -0.53
    BeginContext
    -0.52
    expandindo
    -0.52
     Wer
    -0.51
     "..\..\
    -0.50
    ➞
    -0.50
     "..\..\..\
    -0.50
     utafitiHapana
    -0.49
    POSITIVE LOGITS
    loroethane
    0.56
    DockStyle
    0.56
    everywhere
    0.55
     SIMBAD
    0.54
     rând
    0.53
     Everywhere
    0.52
     Woody
    0.52
    complexContent
    0.51
    RUnlock
    0.51
     épaules
    0.51
    Activations Density 1.171%

    No Known Activations