© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    words relating to negative consequences, movies and representing meaning

    oai_token-act-pair · gemini-2.0-flash

    conversion

    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
     autorytatywna
    -0.71
     дописавши
    -0.50
     виправивши
    -0.47
    RetentionPolicy
    -0.45
     bluza
    -0.45
    IBOutlet
    -0.45
    erializer
    -0.45
     betweenstory
    -0.45
    entrySet
    -0.44
     admiten
    -0.44
    POSITIVE LOGITS
     rendition
    0.63
     Render
    0.59
    PYX
    0.57
     Faithful
    0.57
     rendering
    0.55
     Reproduce
    0.54
     Kanu
    0.53
    ximation
    0.52
     render
    0.52
     Assy
    0.52
    Activations Density 2.886%

    No Known Activations