© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18549
    Prev
    Next
    INDEX
    Explanations

    billy jean, billy budd, billie eilish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     program
    0.39
     fossa
    0.38
     lenght
    0.37
     हाइट
    0.37
    __'
    0.37
    jenkins
    0.36
     PROGRAM
    0.36
    設
    0.36
     uncle
    0.36
    íí
    0.36
    POSITIVE LOGITS
    貂
    0.39
     videre
    0.39
    ajo
    0.38
     প্রজ
    0.38
     eut
    0.37
    Gift
    0.36
     accession
    0.36
    ovat
    0.36
     ارز
    0.36
    ibia
    0.35
    Activations Density 0.009%

    No Known Activations