© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1719
    Prev
    Next
    INDEX
    Explanations

    words associated with aesthetic appreciation, mixed in with instances of the letter sequence "ai"

    oai_token-act-pair · gemini-2.0-flash

    beauty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     beauty
    -1.53
    beauty
    -1.45
    Beauty
    -1.34
     Beauty
    -1.34
     BEAUTY
    -1.27
     belleza
    -1.13
     beauté
    -1.10
    BEAUTY
    -1.10
     beauties
    -1.05
     beleza
    -0.94
    POSITIVE LOGITS
    ستین
    0.47
    mingen
    0.47
    rungsseite
    0.47
     use
    0.44
     non
    0.44
     rev
    0.44
    pygame
    0.42
    orium
    0.42
    Possui
    0.42
    ansa
    0.41
    Activations Density 5.006%

    No Known Activations