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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1946
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to damages, prosecution and judgement in court cases.

    oai_token-act-pair · gemini-2.0-flash

    legal texts about damages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     <=",
    -0.84
    ThroughAttribute
    -0.81
    MigrationBuilder
    -0.79
     betweenstory
    -0.79
    StructEnd
    -0.78
     незавершена
    -0.76
    MemoryWarning
    -0.75
     AssemblyProduct
    -0.75
    ViewImports
    -0.73
    :✨
    -0.72
    POSITIVE LOGITS
     pre
    0.52
    adget
    0.50
    dy
    0.45
     award
    0.43
    Sprintf
    0.43
    NullException
    0.42
    lucene
    0.38
    pre
    0.38
    ナップ
    0.38
     Haushalt
    0.37
    Activations Density 5.513%

    No Known Activations