© 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. 130654
    Prev
    Next
    INDEX
    Explanations

    Val

    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
    uel
    0.42
     निम्
    0.39
     துறை
    0.39
    zynarod
    0.39
     RSD
    0.38
     Oda
    0.38
    ودي
    0.38
    域
    0.38
    uest
    0.37
    uta
    0.37
    POSITIVE LOGITS
    cluded
    0.38
    риса
    0.37
    ресенье
    0.36
    猚
    0.36
    ровкой
    0.36
     Ver
    0.35
    ค้า
    0.35
    함을
    0.35
    ቻል
    0.35
    Sar
    0.34
    Activations Density 0.001%

    No Known Activations