© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5774
    Prev
    Next
    INDEX
    Explanations

    ya / yeah variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    頑張
    0.37
    倾向
    0.37
     właśnie
    0.36
     Zin
    0.36
     Вообще
    0.36
     rooft
    0.35
    }!
    0.35
     Cinque
    0.34
    കൂ
    0.34
    গুলো
    0.34
    POSITIVE LOGITS
     ya
    1.19
     Ya
    0.89
    Ya
    0.84
     YA
    0.77
    ya
    0.72
     يا
    0.71
     yah
    0.70
     я
    0.68
    YA
    0.57
    야
    0.57
    Activations Density 0.412%

    No Known Activations