© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16057
    Prev
    Next
    INDEX
    Explanations

    the word "para" (meaning "for" or "to" in Portuguese/Spanish)

    oai_token-act-pair · gemini-2.0-flash

    para

    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
    -3.00
     Efq
    -2.94
     itſelf
    -2.89
     ―――――
    -2.86
     ་་
    -2.80
     Monfieur
    -2.80
     Theſe
    -2.77
     Anſ
    -2.69
     doubtnut
    -2.67
     auffi
    -2.66
    POSITIVE LOGITS
     
    1.82
    ,
    1.60
     in
    1.60
    <eos>
    1.59
     a
    1.55
     I
    1.53
    .
    1.47
      
    1.43
     (
    1.42
     the
    1.41
    Activations Density 1.090%

    No Known Activations