© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    financial reports or legal documents related to loans, rentals, percentages, and property assessments

    oai_token-act-pair · gemini-2.0-flash

    financial/legal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ğlık
    -0.47
    djangoproject
    -0.47
    солю
    -0.46
     Stump
    -0.46
     wonder
    -0.45
    reflect
    -0.45
     pulumi
    -0.45
    rxjs
    -0.45
     EconPapers
    -0.45
     reflect
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.66
    bayan
    0.57
     '\\;'
    0.56
     TextAppearance
    0.54
     GSA
    0.52
     lenker
    0.50
     cref
    0.50
     ilç
    0.49
    ManagedBean
    0.48
     Isola
    0.47
    Activations Density 26.080%

    No Known Activations