© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4545
    Prev
    Next
    INDEX
    Explanations

    legal and medical terminology in formal documents, including case citations and references to studies or reports

    oai_token-act-pair · gemini-2.0-flash

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    thâu
    -0.53
     Venture
    -0.52
     so
    -0.51
    Apparently
    -0.48
     Apparently
    -0.48
    FileType
    -0.47
     gewor
    -0.46
    FromFile
    -0.44
     rồi
    -0.44
     https
    -0.43
    POSITIVE LOGITS
     itſelf
    0.83
     Cæsar
    0.78
    GEBURTSDATUM
    0.75
     Theſe
    0.71
     occaf
    0.69
     ſeveral
    0.67
    "},
    0.66
     becauſe
    0.66
    ंदीखरीदारी
    0.66
    expandindo
    0.65
    Activations Density 16.891%

    No Known Activations