© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53329
    Prev
    Next
    INDEX
    Explanations

    end of turn markers

    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_31_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
    гель
    0.37
    前の
    0.37
     industrious
    0.37
    GED
    0.37
    牘
    0.36
     setw
    0.35
    Neighborhood
    0.35
    Near
    0.35
     venturing
    0.35
     flipping
    0.34
    POSITIVE LOGITS
    ಟೆ
    0.39
    فر
    0.37
     santi
    0.36
     tuj
    0.36
    တင်း
    0.36
     सांसदों
    0.36
     ನನಗೆ
    0.36
     ফ্রান্স
    0.35
    𝐯
    0.35
     aberto
    0.35
    Activations Density 0.001%

    No Known Activations