© 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. 57277
    Prev
    Next
    INDEX
    Explanations

    verbs

    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
    .
    0.45
     is
    0.44
    ide
    0.44
     doesn
    0.41
     духов
    0.41
    ocles
    0.39
     гос
    0.39
    ies
    0.38
    s
    0.38
     მხ
    0.37
    POSITIVE LOGITS
     করছে
    0.55
     consegue
    0.55
     করেছে
    0.54
     পেয়েছে
    0.54
     devra
    0.50
     bekommt
    0.50
     পাচ্ছে
    0.50
     করিবে
    0.48
     encontrará
    0.48
     deberá
    0.47
    Activations Density 0.000%

    No Known Activations