© 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. 419
    Prev
    Next
    INDEX
    Explanations

    titles of creative works, particularly movies and songs, as well as some words associated with those titles.

    oai_token-act-pair · gemini-2.0-flash

    movies and media

    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
    BagConstraints
    -0.46
    .
    -0.45
    orthand
    -0.45
     beroep
    -0.40
    Blueprint
    -0.40
    softc
    -0.40
     resistenza
    -0.39
     thừa
    -0.39
     bezpieczeństwa
    -0.38
    šanas
    -0.38
    POSITIVE LOGITS
    发表于
    0.83
    原始内容存档于
    0.82
    出版年
    0.74
     فريبيس
    0.72
    ISupport
    0.71
    jectures
    0.71
     مرئيه
    0.71
    gonic
    0.69
     שוליים
    0.69
    PhysRev
    0.68
    Activations Density 0.676%

    No Known Activations