© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12421
    Prev
    Next
    INDEX
    Explanations

    the word "package" and words like "import" or "outside" that often appear toward the beginning of a line of code.

    oai_token-act-pair · gemini-2.0-flash

    package or outside

    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
     myſelf
    -1.09
     himſelf
    -1.02
     itſelf
    -1.02
     Mahomet
    -1.01
     becauſe
    -0.99
     Shaksp
    -0.98
     Shakspeare
    -0.98
     ſhe
    -0.97
     themſelves
    -0.96
     vPvB
    -0.95
    POSITIVE LOGITS
     the
    0.79
     a
    0.76
    ↵↵
    0.72
     it
    0.67
     I
    0.64
    <eos>
    0.63
     A
    0.63
     
    0.62
     R
    0.62
      
    0.60
    Activations Density 2.125%

    No Known Activations