© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13417
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that are descriptive or comparative, or that relate to interaction or serial progression

    oai_token-act-pair · gemini-2.0-flash

    individually, alone, one at a time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    EditorBrowsable
    -0.60
    ranslated
    -0.55
    ActivityResult
    -0.54
    iotensin
    -0.52
    fcntl
    -0.50
    tega
    -0.50
    getSystemService
    -0.49
    openssl
    -0.47
    StoryboardSegue
    -0.47
    Примечания
    -0.47
    POSITIVE LOGITS
     ziua
    0.57
     facciamo
    0.56
     venons
    0.54
     églises
    0.50
    Sucesor
    0.49
     mères
    0.48
     bezeichneter
    0.47
     disambiguazione
    0.47
     reemplazo
    0.47
     bâton
    0.46
    Activations Density 2.702%

    No Known Activations