© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6327
    Prev
    Next
    INDEX
    Explanations

    legal, contractual, and bureaucratic language

    oai_token-act-pair · gemini-2.0-flash

    legal texts

    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
    &
    -0.62
    mybatisplus
    -0.61
    AccessorTable
    -0.56
    ThroughAttribute
    -0.49
     &
    -0.47
    ように
    -0.45
    تقاوى
    -0.44
    igeon
    -0.44
    \&
    -0.43
    стру
    -0.43
    POSITIVE LOGITS
     end
    1.51
     ami
    1.09
     aud
    1.05
     mid
    1.00
     sad
    0.94
     End
    0.94
     amt
    0.93
     aad
    0.93
     ana
    0.93
    end
    0.90
    Activations Density 1.863%

    No Known Activations