© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2997
    Prev
    Next
    INDEX
    Explanations

    words strongly related to business accounting

    oai_token-act-pair · gemini-2.0-flash

    Accounting/Configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     AssemblyCulture
    -0.93
     Efq
    -0.86
     MainAxisSize
    -0.79
    tagHelperRunner
    -0.77
    IUrlHelper
    -0.76
    SharedDtor
    -0.76
     Monfieur
    -0.75
     myſelf
    -0.73
    MLLoader
    -0.73
    criminator
    -0.73
    POSITIVE LOGITS
     receiving
    0.49
     PR
    0.48
    tent
    0.47
     susu
    0.46
    istoitu
    0.46
     mo
    0.45
    attr
    0.45
     claim
    0.45
     charged
    0.45
     Tent
    0.45
    Activations Density 5.684%

    No Known Activations