© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206523
    Prev
    Next
    INDEX
    Explanations

    Lipp, Ripp, ipp, pp suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    смо
    0.38
    ристи
    0.37
    禎
    0.36
     бө
    0.36
    </td>
    0.35
    гон
    0.35
     collabor
    0.34
     dop
    0.34
     coton
    0.34
     رہیں
    0.34
    POSITIVE LOGITS
    ltal
    0.41
    cross
    0.38
    triple
    0.37
     triple
    0.35
    hose
    0.35
    main
    0.34
     @_
    0.34
     runApp
    0.34
    カイブ
    0.34
    product
    0.33
    Activations Density 0.000%

    No Known Activations