© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219395
    Prev
    Next
    INDEX
    Explanations

    articles

    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_47_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gye
    0.42
    crumbs
    0.38
    lyPlugin
    0.38
    вана
    0.38
     crumbs
    0.38
    myData
    0.38
    ورس
    0.37
    }^{-
    0.37
    uar
    0.37
    monte
    0.36
    POSITIVE LOGITS
     Innocent
    0.43
    祿
    0.41
     innocent
    0.36
    schemaLocation
    0.36
     pade
    0.35
    ходов
    0.34
     স্বায়ত্ত
    0.34
     M
    0.34
     ns
    0.33
     Moor
    0.33
    Activations Density 0.004%

    No Known Activations