© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4757
    Prev
    Next
    INDEX
    Explanations

    segments of legal opinions that discuss "the ends of justice."

    oai_token-act-pair · gemini-2.0-flash

    career advancement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IGraphics
    -0.94
     habet
    -0.90
     Efq
    -0.87
    queryInterface
    -0.86
    saraba
    -0.82
     Roskov
    -0.81
     jLabel
    -0.80
     незавершена
    -0.79
    SequentialGroup
    -0.79
     ThemeData
    -0.77
    POSITIVE LOGITS
     advance
    0.55
     promotion
    0.51
    advance
    0.50
     further
    0.47
     advanced
    0.46
     promoted
    0.46
    Advance
    0.46
    vancing
    0.45
     promote
    0.45
     promo
    0.43
    Activations Density 3.595%

    No Known Activations