© 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. 195454
    Prev
    Next
    INDEX
    Explanations

    often

    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
    performance
    0.40
    icions
    0.39
    cul
    0.37
    bloc
    0.36
    Performance
    0.36
     Dir
    0.36
    രിച്ചി
    0.36
    冂
    0.35
    流量
    0.35
    쥴
    0.35
    POSITIVE LOGITS
     covered
    0.48
     african
    0.42
     wearing
    0.41
     unarmed
    0.40
     exothermic
    0.40
     chris
    0.40
     configur
    0.39
     ஆரோ
    0.39
     arrang
    0.39
     christmas
    0.38
    Activations Density 0.008%

    No Known Activations