© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9528
    Prev
    Next
    INDEX
    Explanations

    references to insignias, emblems, or markings of an organization or ideology on clothing or property

    oai_token-act-pair · gemini-2.0-flash

    symbols on apparel/items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    adaptiveStyles
    -0.65
    tagHelperRunner
    -0.62
    Geplaatst
    -0.56
    kloped
    -0.54
    ContentAsync
    -0.53
    principalTable
    -0.52
     <<<<<<<<<<<<<<
    -0.51
     symboles
    -0.50
    impresa
    -0.50
     transfieras
    -0.50
    POSITIVE LOGITS
    ContextHolder
    0.51
    yorsunuz
    0.47
    ksesta
    0.47
    WithIOException
    0.47
    MimeType
    0.46
     domy
    0.45
    nil
    0.44
    couvrez
    0.44
    athie
    0.44
    acherous
    0.43
    Activations Density 18.840%

    No Known Activations