© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6597
    Prev
    Next
    INDEX
    Explanations

    references to the Supreme Court and constitutional law

    oai_token-act-pair · gemini-2.0-flash

    references to the Supreme Court

    np_token-act-pair-logits · gpt-4o-mini

    Supreme

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    httphttps
    -0.82
    IActionResult
    -0.63
     الحره
    -0.58
     Dif
    -0.47
    Bou
    -0.47
     pulumi
    -0.45
    relsen
    -0.44
    riwal
    -0.44
    发表于
    -0.44
     onPostExecute
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.64
    usermodel
    0.59
    uxxxx
    0.59
    atamente
    0.55
    ViewFeatures
    0.54
    Diweddarwch
    0.53
     Lest
    0.53
    queryInterface
    0.53
     vectorielle
    0.52
     Shetty
    0.50
    Activations Density 0.515%

    No Known Activations