© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13075
    Prev
    Next
    INDEX
    Explanations

    phrases that are awards or nominations for best film-related achievements

    oai_token-act-pair · gemini-2.0-flash

    Golden Globe nominations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ospels
    -0.57
     виправивши
    -0.57
    prits
    -0.54
    ViewImports
    -0.52
     الحره
    -0.52
     Vern
    -0.52
    Inbound
    -0.52
    yim
    -0.52
    toplankton
    -0.52
     Seligman
    -0.51
    POSITIVE LOGITS
    <bos>
    1.31
    Palmarès
    0.62
     médaille
    0.59
    '")
    0.59
     Award
    0.57
    Medal
    0.57
     Medal
    0.57
     award
    0.56
    Auszeichnungen
    0.56
     awards
    0.56
    Activations Density 0.733%

    No Known Activations