© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11512
    Prev
    Next
    INDEX
    Explanations

    Baywatch Hawaii show babe

    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_13_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
     Bhand
    0.61
     Caputo
    0.55
    raded
    0.54
    rono
    0.52
    照射
    0.52
     ವಿಷಯ
    0.51
    抔
    0.51
     Facility
    0.50
     Caso
    0.50
    Կ
    0.49
    POSITIVE LOGITS
     televisão
    0.54
     television
    0.53
     テレビ
    0.52
     تلویزی
    0.52
     televisi
    0.52
     kinh
    0.51
     ফেলেছে
    0.51
     telah
    0.50
     mencapai
    0.49
     aerial
    0.48
    Activations Density 0.018%

    No Known Activations