© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7295
    Prev
    Next
    INDEX
    Explanations

    references to a specific model of car and its features

    oai_token-act-pair · gemini-2.0-flash

    coatings, colors, appearance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    mane
    -0.49
    ougou
    -0.46
    hyr
    -0.44
    ElementException
    -0.44
    renço
    -0.43
     Conservancy
    -0.42
    DeviceType
    -0.42
    aze
    -0.41
    立ち
    -0.41
    DIAG
    -0.40
    POSITIVE LOGITS
    __":
    0.84
     EconPapers
    0.80
     oprot
    0.79
    IUrlHelper
    0.78
     painting
    0.77
     متعلقه
    0.75
    __':
    0.75
     satin
    0.74
    queryInterface
    0.73
    __":
    0.73
    Activations Density 1.458%

    No Known Activations