© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4529
    Prev
    Next
    INDEX
    Explanations

    instances in which a question, issue, or tax is being raised

    oai_token-act-pair · gemini-2.0-flash

    raise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     raised
    -2.80
     raise
    -2.72
     raising
    -2.56
     Raised
    -2.39
     raises
    -2.38
     Raising
    -2.36
    Raising
    -2.31
     Raise
    -2.28
    raise
    -2.23
    raised
    -2.23
    POSITIVE LOGITS
    tvguidetime
    0.66
    Referanser
    0.63
    Referències
    0.52
    脚注の使い方
    0.52
    Hentet
    0.51
     blessures
    0.50
    ือน
    0.48
     médicale
    0.47
    ✨:
    0.47
     smer
    0.47
    Activations Density 7.541%

    No Known Activations