© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10101
    Prev
    Next
    INDEX
    Explanations

    references to movies and TV shows, especially science fiction

    oai_token-act-pair · gemini-2.0-flash

    Sci-fi, technology, and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ✷
    -0.53
     Lune
    -0.52
     frit
    -0.50
     gree
    -0.49
     Klon
    -0.48
     Spare
    -0.47
    AndEndTag
    -0.47
     Deckel
    -0.47
    Према
    -0.47
     ὅ
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.60
     dégust
    0.59
    timewa
    0.57
    setVerticalGroup
    0.54
    StoryboardSegue
    0.53
    OrBuilder
    0.53
     تضيفلها
    0.52
     ArrayAdapter
    0.52
     initComponents
    0.52
    InputTagHelper
    0.52
    Activations Density 0.205%

    No Known Activations