© 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. 6125
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "MD" (Medical Doctor) or a very similar sequence of the letters "m" and "d" adjacent to each other

    oai_token-act-pair · gemini-2.0-flash

    MD

    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
     
    -1.03
     the
    -0.83
     a
    -0.79
     (
    -0.72
     I
    -0.71
     for
    -0.71
     <
    -0.68
    :
    -0.68
    .
    -0.68
     R
    -0.67
    POSITIVE LOGITS
    Personensuche
    1.52
     متعلقه
    1.45
     myſelf
    1.40
     itſelf
    1.34
     Monfieur
    1.33
    <unused47>
    1.32
    <unused6>
    1.31
    <unused8>
    1.31
    <unused3>
    1.31
    <pad>
    1.31
    Activations Density 0.555%

    No Known Activations