© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5538
    Prev
    Next
    INDEX
    Explanations

    words related to legal liability and judgements

    oai_token-act-pair · gemini-2.0-flash

    legal responsibility

    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
    ftagPool
    -0.62
     sánh
    -0.59
     midnight
    -0.56
     Devonian
    -0.55
     AppBundle
    -0.54
    EDEFAULT
    -0.54
    IContainer
    -0.54
    HasForeignKey
    -0.53
     GIPHY
    -0.53
    tawesome
    -0.52
    POSITIVE LOGITS
    !*\
    0.60
    存于互联网档案馆
    0.57
     agreed
    0.51
    Agreed
    0.49
    DetailView
    0.49
    $_['
    0.49
    PerformLayout
    0.48
    ERVIS
    0.47
     doGet
    0.47
    atalos
    0.46
    Activations Density 11.526%

    No Known Activations