© 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. 76860
    Prev
    Next
    INDEX
    Explanations

    extra

    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
     detached
    0.39
    ahi
    0.37
    erys
    0.37
    spaced
    0.36
     Oder
    0.35
     Canonical
    0.35
    ANU
    0.35
    ່
    0.35
     suff
    0.34
    érg
    0.34
    POSITIVE LOGITS
     extra
    2.73
    Extra
    2.61
    extra
    2.55
     Extra
    2.55
     ekstra
    2.22
    EXTRA
    2.20
     EXTRA
    2.16
     экстра
    1.50
    额外
    1.45
    额外的
    1.28
    Activations Density 0.186%

    No Known Activations