© 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. 13107
    Prev
    Next
    INDEX
    Explanations

    the word "appropriate" and some legal/medical terms.

    oai_token-act-pair · gemini-2.0-flash

    appropriate

    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
    ^(@)
    -1.06
     $_"
    -1.04
    "):
    -1.02
     %@",
    -0.99
     \\
    -0.95
    $")
    -0.93
     ―――――
    -0.93
     ་་
    -0.93
    .",
    -0.91
    ⿷
    -0.90
    POSITIVE LOGITS
    ので
    0.66
     (
    0.56
    事で
    0.55
      
    0.54
    le
    0.51
     
    0.51
    <eos>
    0.50
    This
    0.48
     nha
    0.48
    stanbul
    0.47
    Activations Density 1.358%

    No Known Activations