© 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. 15200
    Prev
    Next
    INDEX
    Explanations

    the adjective "loyal" and related words like "banned"

    oai_token-act-pair · gemini-2.0-flash

    loyal

    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
     
    -1.63
    ,
    -1.10
     (
    -1.10
     I
    -1.08
    ↵↵
    -1.06
      
    -0.98
     K
    -0.97
     in
    -0.96
     the
    -0.95
     [
    -0.95
    POSITIVE LOGITS
     Monfieur
    2.17
     Efq
    2.14
     Theſe
    2.05
     Houſe
    1.95
     Reſ
    1.91
     houſe
    1.87
     Majefty
    1.80
     Jefus
    1.78
     pleaſure
    1.78
     Cæsar
    1.77
    Activations Density 2.147%

    No Known Activations