© 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. 14087
    Prev
    Next
    INDEX
    Explanations

    the letter U followed by a period, especially as part of "U.S."

    oai_token-act-pair · gemini-2.0-flash

    U

    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
    ResumeLayout
    -0.60
    usar
    -0.55
    ArgumentParser
    -0.53
    moveToFirst
    -0.51
     GenerationType
    -0.51
    ल्प
    -0.51
    HomeAsUpEnabled
    -0.50
    expandindo
    -0.50
    ooc
    -0.49
    DllImport
    -0.49
    POSITIVE LOGITS
     الدولى
    0.70
     jsPsych
    0.60
    انجليز
    0.59
    ‚¬
    0.57
     Anſ
    0.54
     Middles
    0.52
    脚注の使い方
    0.52
     raiſ
    0.52
     ainfi
    0.52
    pters
    0.51
    Activations Density 0.457%

    No Known Activations