© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4196
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in court or legislative documents

    oai_token-act-pair · gemini-2.0-flash

    at

    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
     незавершена
    -0.95
    WaitGroup
    -0.94
    ]--;
    -0.91
    ReusableCell
    -0.88
    CompilerServices
    -0.79
    XmlAccessorType
    -0.79
    PyExc
    -0.77
     jspb
    -0.77
    ">//
    -0.77
    PerformLayout
    -0.76
    POSITIVE LOGITS
     at
    2.63
    At
    1.69
     At
    1.62
    at
    1.60
     tại
    1.09
     AT
    1.05
     	e
    0.81
    @
    0.76
     ở
    0.71
    AtIndex
    0.69
    Activations Density 2.506%

    No Known Activations