© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 313
    Prev
    Next
    INDEX
    Explanations

    polite and respectful

    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_44_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
    replay
    0.41
    ImageList
    0.39
    琊
    0.37
    WL
    0.37
     гран
    0.37
     distract
    0.36
     ప్రే
    0.36
    派
    0.36
     scape
    0.35
    oplane
    0.35
    POSITIVE LOGITS
     polite
    2.06
     politely
    1.82
     Polite
    1.80
     courteous
    1.63
     courtesy
    1.43
    Pol
    1.37
    pol
    1.34
     Courtesy
    1.33
     polit
    1.30
     respectfully
    1.29
    Activations Density 0.345%

    No Known Activations