© 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. 162806
    Prev
    Next
    INDEX
    Explanations

    the pronoun "you"

    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
     można
    0.37
    便利な
    0.37
     можна
    0.35
    难
    0.35
     interst
    0.35
    rors
    0.34
     dificult
    0.34
    長的
    0.34
     can
    0.33
     difficult
    0.33
    POSITIVE LOGITS
     видеть
    0.39
    ukai
    0.37
     स्पीकर
    0.36
     keltiradi
    0.36
     kirk
    0.35
    ;.
    0.35
     вста
    0.34
    uti
    0.34
    ហើយ
    0.34
    خی
    0.34
    Activations Density 0.004%

    No Known Activations