© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83338
    Prev
    Next
    INDEX
    Explanations

    commas

    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_53_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
     namely
    0.41
     например
    0.39
     yaitu
    0.38
     yakni
    0.37
     odnosno
    0.37
     Namely
    0.35
     例如
    0.35
     although
    0.34
    например
    0.34
     즉
    0.33
    POSITIVE LOGITS
    nergie
    0.25
    enes
    0.24
    ］
    0.24
    কারে
    0.24
    ｎ
    0.23
    大法
    0.23
    ercise
    0.23
    ."—
    0.23
    னும்
    0.23
    )…
    0.23
    Activations Density 0.013%

    No Known Activations