© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9770
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "ensure" (and/or variants) specifying a condition for something being true

    oai_token-act-pair · gemini-2.0-flash

    ensure/insure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    原始内容存档于
    -0.94
     оригіналу
    -0.92
     يتيمه
    -0.87
     كومونز
    -0.82
    AndEndTag
    -0.77
    WebVitals
    -0.77
    BeginContext
    -0.74
    PerformLayout
    -0.74
    الإنجليزية
    -0.71
    SequentialGroup
    -0.69
    POSITIVE LOGITS
     that
    0.90
     there
    0.76
     to
    0.50
     inter
    0.49
     That
    0.49
     all
    0.49
     no
    0.48
     total
    0.48
     the
    0.47
    Palindrome
    0.47
    Activations Density 6.154%

    No Known Activations