© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5096
    Prev
    Next
    INDEX
    Explanations

    words related to fictional superpowers and science fiction

    oai_token-act-pair · gemini-2.0-flash

    Violent and fantastical narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ClCompile
    -0.82
     typelib
    -0.72
    ыгана
    -0.68
    хьтан
    -0.68
    исленность
    -0.66
    Hentet
    -0.66
    PerformLayout
    -0.65
     useAppContext
    -0.64
    ziasztok
    -0.64
     transfieras
    -0.63
    POSITIVE LOGITS
    发表于
    0.41
    zają
    0.41
     always
    0.41
    AsUp
    0.40
    estanden
    0.40
    essions
    0.40
    testng
    0.37
    styles
    0.36
    zonego
    0.36
    GenerationType
    0.36
    Activations Density 24.218%

    No Known Activations