© 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. 195131
    Prev
    Next
    INDEX
    Explanations

    image

    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
     rum
    0.42
     appropriation
    0.39
    업
    0.38
     SBS
    0.38
     اﻻ
    0.37
    Resp
    0.37
     রুপ
    0.37
    Следу
    0.36
     bipartisan
    0.35
     পাচ
    0.35
    POSITIVE LOGITS
    몰
    0.40
    🥭
    0.37
     те
    0.37
     tế
    0.37
    েন্টে
    0.37
    mitting
    0.36
    Myth
    0.35
    assung
    0.35
     মতে
    0.35
     Baths
    0.35
    Activations Density 0.003%

    No Known Activations