© 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. 237435
    Prev
    Next
    INDEX
    Explanations

    say ","

    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
     provide
    0.38
     invitation
    0.37
     говорит
    0.37
     there
    0.37
     reply
    0.37
     사람은
    0.36
     વ્યક્તિ
    0.36
     Invitation
    0.36
    䁂
    0.36
     wick
    0.35
    POSITIVE LOGITS
    ATEG
    0.41
    dwelling
    0.41
     dwelt
    0.39
    ingale
    0.37
    took
    0.37
    ŵ
    0.37
    Area
    0.36
     наз
    0.36
    出場
    0.35
    Difficult
    0.35
    Activations Density 0.001%

    No Known Activations