© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 55166
    Prev
    Next
    INDEX
    Explanations

    xx

    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_55_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
     okay
    0.42
     OK
    0.40
     Okay
    0.40
     ok
    0.38
    ectl
    0.38
    %{
    0.37
     конечно
    0.37
     COURT
    0.37
     oku
    0.35
    esterly
    0.35
    POSITIVE LOGITS
    Craw
    0.38
    '')
    0.36
    ,)
    0.34
    ).(
    0.34
     ())
    0.34
     '')
    0.34
    )(
    0.33
     جاه
    0.33
    ));
    0.32
     (,
    0.32
    Activations Density 0.001%

    No Known Activations