© 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. 11691
    Prev
    Next
    INDEX
    Explanations

    the word "entertain" or the phrase "ends of justice"

    oai_token-act-pair · gemini-2.0-flash

    entertain

    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
      
    -0.74
     I
    -0.71
     Y
    -0.69
     his
    -0.67
     K
    -0.67
     kasarigan
    -0.65
     the
    -0.63
    mergeFrom
    -0.62
    hitheater
    -0.60
     svo
    -0.60
    POSITIVE LOGITS
     Shakspeare
    1.14
     itſelf
    1.12
     Houſe
    1.09
     Jefus
    1.07
     Reſ
    1.05
     Eſ
    1.02
     againſt
    1.01
     myſelf
    1.00
     ་་
    1.00
     Anſ
    0.98
    Activations Density 1.633%

    No Known Activations