© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253733
    Prev
    Next
    INDEX
    Explanations

    Japanese politeness

    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_56_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
     걸
    0.45
    Do
    0.42
     Do
    0.41
     خال
    0.38
     do
    0.38
    걸
    0.37
     avanç
    0.36
    ಲೆಂ
    0.35
    By
    0.34
    ForRule
    0.34
    POSITIVE LOGITS
    skie
    0.38
     STEELS
    0.37
     Laurence
    0.36
    скія
    0.35
     செய்தால்
    0.35
    pev
    0.35
     పె
    0.34
    厈
    0.34
    ρον
    0.33
    oding
    0.33
    Activations Density 0.000%

    No Known Activations