© 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. 207533
    Prev
    Next
    INDEX
    Explanations

    y

    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
     သူမ
    0.41
    institut
    0.39
     ρ
    0.38
     Monroe
    0.37
     Sonja
    0.36
     INSTIT
    0.36
     ರ
    0.35
     Р
    0.35
     अपना
    0.35
    óch
    0.35
    POSITIVE LOGITS
    ifeng
    0.39
     fascin
    0.36
    蛳
    0.36
    ییر
    0.36
    ference
    0.35
    Comput
    0.34
    ERT
    0.34
    peed
    0.34
    ційних
    0.34
    жнему
    0.34
    Activations Density 0.007%

    No Known Activations