© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85538
    Prev
    Next
    INDEX
    Explanations

    end-stage renal disease

    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_18_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
    實際
    0.50
    mdan
    0.50
    нами
    0.49
    джа
    0.49
     thoracique
    0.48
    鉾
    0.46
     planejamento
    0.45
     calma
    0.44
    adi
    0.44
    ᡵ
    0.43
    POSITIVE LOGITS
     sheds
    0.47
     up
    0.47
     occurs
    0.47
    しまいます
    0.45
     spør
    0.45
    拗
    0.44
     about
    0.43
     doesn
    0.43
     liquids
    0.43
     arises
    0.43
    Activations Density 0.000%

    No Known Activations