© 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. 5694
    Prev
    Next
    INDEX
    Explanations

    the word "residents" and words/names associated with geographic planning

    oai_token-act-pair · gemini-2.0-flash

    residents

    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
     Efq
    -1.56
     myſelf
    -1.52
    ſelf
    -1.50
     themſelves
    -1.47
    ſelves
    -1.45
     pleaſure
    -1.42
     auffi
    -1.41
     Monfieur
    -1.41
     Jefus
    -1.40
     itſelf
    -1.40
    POSITIVE LOGITS
    ,
    0.93
     
    0.84
    -
    0.80
      
    0.77
     and
    0.77
     in
    0.74
     (
    0.72
     –
    0.69
    /
    0.69
     on
    0.66
    Activations Density 1.522%

    No Known Activations