© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131270
    Prev
    Next
    INDEX
    Explanations

    fatal diseases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Bog
    0.41
     आलम
    0.38
    NULL
    0.37
    Kir
    0.37
     കണ്ണ
    0.37
    爪
    0.37
     전시
    0.36
     NULL
    0.36
    ಜ
    0.35
    AVE
    0.35
    POSITIVE LOGITS
    हल
    0.50
     nan
    0.49
     incur
    0.49
     असा
    0.45
     लाइ
    0.43
     Hal
    0.43
     مه
    0.43
     لاع
    0.42
     Akufo
    0.41
     incurring
    0.40
    Activations Density 0.009%

    No Known Activations