© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69491
    Prev
    Next
    INDEX
    Explanations

    role playing

    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_46_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
     starring
    0.56
     geworden
    0.49
     становятся
    0.45
     becoming
    0.45
     starred
    0.41
     devient
    0.40
     become
    0.40
     roles
    0.39
     становится
    0.39
    }^{*}(\
    0.39
    POSITIVE LOGITS
    ongyang
    0.40
    กก
    0.40
    詁
    0.40
    转载
    0.38
    )\|_{\
    0.37
     मातर
    0.37
    PRESENT
    0.37
     اشرف
    0.36
     Revised
    0.36
    റേ
    0.36
    Activations Density 0.009%

    No Known Activations