© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 65602
    Prev
    Next
    INDEX
    Explanations

    Japanese culture

    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_51_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
    tsz
    0.38
    امة
    0.38
    喹
    0.38
    Juan
    0.37
     JUAN
    0.37
     Valdez
    0.37
    庻
    0.36
    晠
    0.36
     CRC
    0.35
    Grat
    0.35
    POSITIVE LOGITS
    ائيل
    0.42
     Hors
    0.40
     Wo
    0.39
     falsch
    0.39
    ेल
    0.39
     Obtaining
    0.38
    eradish
    0.38
    Hors
    0.38
    鈮
    0.38
     fett
    0.37
    Activations Density 0.005%

    No Known Activations