© 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. 63967
    Prev
    Next
    INDEX
    Explanations

    elegance

    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
    ate
    0.80
    ATE
    0.58
    al
    0.50
    ală
    0.49
    לי
    0.47
    atein
    0.46
    ल
    0.45
    ORMAL
    0.44
    ICES
    0.44
    ادی
    0.42
    POSITIVE LOGITS
     Non
    0.36
     che
    0.36
    するのは
    0.36
    താ
    0.36
     **
    0.35
     Nbd
    0.35
     Che
    0.34
    的是
    0.34
    ujte
    0.34
    ant
    0.34
    Activations Density 0.000%

    No Known Activations