© 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. 152058
    Prev
    Next
    INDEX
    Explanations

    names

    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
    不
    0.48
     ellen
    0.38
    ूर
    0.37
    ুরের
    0.36
    ív
    0.35
    ció
    0.35
    è
    0.35
     なる
    0.35
    を含
    0.34
     wallet
    0.34
    POSITIVE LOGITS
     Kar
    0.45
     Lina
    0.43
     Ale
    0.42
     Kl
    0.39
     Auguste
    0.39
     Clas
    0.39
    Dix
    0.38
    CAPT
    0.38
     Taft
    0.37
     Але
    0.36
    Activations Density 0.000%

    No Known Activations