© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47173
    Prev
    Next
    INDEX
    Explanations

    role-playing "you are a"

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ва
    0.75
    م
    0.73
    м
    0.71
     ovales
    0.70
    ра
    0.68
    й
    0.68
     Aix
    0.68
    一個
    0.67
    ся
    0.66
     люди
    0.66
    POSITIVE LOGITS
    a
    1.05
    া
    0.77
    I
    0.72
    ،
    0.71
    ，
    0.66
    ="
    0.64
    inę
    0.63
    ，“
    0.63
    。“
    0.63
    in
    0.62
    Activations Density 0.026%

    No Known Activations