© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90447
    Prev
    Next
    INDEX
    Explanations

    mocking behavior and responses

    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_23_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
     মিসেস
    0.46
     Mrs
    0.43
     secondi
    0.42
    譙
    0.38
    Mrs
    0.37
    曛
    0.36
     таке
    0.36
     >>>
    0.36
    fourths
    0.36
     হয়েছিল
    0.35
    POSITIVE LOGITS
    elij
    0.39
    quadratic
    0.39
    td
    0.38
    leadership
    0.38
    democratic
    0.38
    zyk
    0.38
    Beijing
    0.38
    responsive
    0.38
    ree
    0.37
    leader
    0.37
    Activations Density 0.000%

    No Known Activations