© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145570
    Prev
    Next
    INDEX
    Explanations

    /

    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_59_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
     ८
    0.58
    *,
    0.49
    *.
    0.48
     ٣
    0.48
    **(
    0.47
     ۱۵
    0.46
     ५
    0.46
    *(
    0.45
     ۸
    0.45
     ३
    0.44
    POSITIVE LOGITS
    ?
    0.54
     /
    0.44
    igning
    0.39
    !
    0.39
    德
    0.39
     Tanzania
    0.38
    ?“
    0.38
     component
    0.37
     many
    0.37
     issue
    0.37
    Activations Density 0.000%

    No Known Activations