© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49437
    Prev
    Next
    INDEX
    Explanations

    Korean language elements

    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_55_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
    状態で
    0.50
    ものを
    0.48
     illustrates
    0.47
    ?",
    0.44
    画像を
    0.44
     illustrating
    0.43
    ?")
    0.43
     ს
    0.43
     illustrate
    0.42
    データを
    0.42
    POSITIVE LOGITS
     및
    0.40
     тех
    0.39
     제시
    0.39
     Ere
    0.38
     있음
    0.38
     Mab
    0.38
     그리고
    0.38
    anged
    0.37
    โดย
    0.37
     HIS
    0.37
    Activations Density 0.001%

    No Known Activations