© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12095
    Prev
    Next
    INDEX
    Explanations

    terms related to spreadsheets, measurements, recipe review comments, software source code, and SQL database commands

    oai_token-act-pair · gemini-2.0-flash

    table

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.67
    __':
    -0.66
    CreateModel
    -0.64
     tabPage
    -0.62
     estekak
    -0.61
    AddTagHelper
    -0.61
    verständlich
    -0.61
    críbete
    -0.60
    ctibles
    -0.60
    ::~
    -0.60
    POSITIVE LOGITS
    rrggbb
    0.61
    classnames
    0.51
     wisata
    0.44
     touristes
    0.43
     namelijk
    0.42
     CreateTagHelper
    0.42
    WidgetItem
    0.42
     séjours
    0.41
    IndentedString
    0.40
    yser
    0.40
    Activations Density 10.069%

    No Known Activations