© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6491
    Prev
    Next
    INDEX
    Explanations

    the word remote alone or with nearby letters such as the word "man", single letter acronyms, and the word "live"

    oai_token-act-pair · gemini-2.0-flash

    remote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ſelf
    -1.45
     Anſ
    -1.41
     Theſe
    -1.38
     Monfieur
    -1.38
     purpoſe
    -1.33
     myſelf
    -1.32
     Majefty
    -1.29
     auffi
    -1.29
     ―――――
    -1.28
     Diſ
    -1.27
    POSITIVE LOGITS
    ↵↵
    0.91
    ↵
    0.88
     
    0.79
    <bos>
    0.76
     (
    0.74
    -
    0.74
     d
    0.71
     and
    0.66
    1
    0.65
      
    0.64
    Activations Density 1.664%

    No Known Activations