© 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. 36589
    Prev
    Next
    INDEX
    Explanations

    Air Rahul

    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
    คว
    0.41
     Aki
    0.40
     Teg
    0.39
     Yus
    0.39
    ど
    0.37
    >¯</
    0.36
    ква
    0.36
     Gly
    0.36
    metry
    0.36
    借
    0.35
    POSITIVE LOGITS
     Air
    0.43
    Air
    0.42
    Rahul
    0.41
    hpp
    0.40
     Rahul
    0.39
     الهواء
    0.38
    houn
    0.37
    raum
    0.37
    राहुल
    0.37
     राहुल
    0.36
    Activations Density 0.001%

    No Known Activations