© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14574
    Prev
    Next
    INDEX
    Explanations

    arguments in favor of alternatives to the Affordable Care Act

    oai_token-act-pair · gemini-2.0-flash

    healthcare

    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
    parsedMessage
    -0.89
    aarrggbb
    -0.87
    PhysRev
    -0.79
     bezeichneter
    -0.73
    دانشنامهٔ
    -0.69
    WriteBarrier
    -0.67
     виправивши
    -0.65
    AnchorStyles
    -0.65
    󠁴
    -0.63
     CreateTagHelper
    -0.63
    POSITIVE LOGITS
     choice
    0.56
    addGap
    0.48
     CHOICE
    0.47
    choice
    0.45
    engel
    0.43
    Choice
    0.42
     competition
    0.41
     tort
    0.41
    CRIPTION
    0.41
     choices
    0.40
    Activations Density 1.003%

    No Known Activations