Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14689
    Prev
    Next
    INDEX
    Explanations

    references to particular TV shows or movies, including their titles but also potentially associated musical acts

    oai_token-act-pair · gemini-2.0-flash

    Six Million Dollar Man

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.90
    ImageContext
    -0.88
    QMetaType
    -0.85
    Datuak
    -0.83
    expandindo
    -0.82
    PreInfinity
    -0.77
     snippetHide
    -0.74
    AutoSize
    -0.74
    clusal
    -0.73
    ChildScrollView
    -0.72
    POSITIVE LOGITS
     Mag
    0.56
    PHeader
    0.49
     b
    0.48
    Mag
    0.44
     o
    0.44
    тє
    0.44
     Mad
    0.42
     mag
    0.42
    uker
    0.42
     Maguire
    0.42
    Activations Density 0.427%

    No Known Activations