© 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. 14700
    Prev
    Next
    INDEX
    Explanations

    the word "space" or words relating to citizenship status

    oai_token-act-pair · gemini-2.0-flash

    space

    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
     Monfieur
    -1.77
     pleaſure
    -1.62
     Efq
    -1.61
     Anſ
    -1.59
     étoient
    -1.59
     myſelf
    -1.59
     avoient
    -1.56
     Majefty
    -1.55
     Theſe
    -1.55
     Jefus
    -1.55
    POSITIVE LOGITS
    <eos>
    0.86
    ↵↵
    0.81
     I
    0.73
     "
    0.72
     (
    0.69
    ↵
    0.67
      
    0.67
    ..
    0.66
    ,
    0.66
     «
    0.66
    Activations Density 1.818%

    No Known Activations