© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82950
    Prev
    Next
    INDEX
    Explanations

    Jack

    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_53_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
    :#
    0.41
     Lampang
    0.39
    可在
    0.38
     часу
    0.38
     elevator
    0.37
     cant
    0.37
     lamented
    0.37
     premat
    0.37
    Upgradeable
    0.36
     W
    0.36
    POSITIVE LOGITS
    будь
    0.42
     ಗು
    0.42
     स्टार
    0.41
     ква
    0.41
     guilds
    0.40
     ارت
    0.40
     гу
    0.39
     guild
    0.39
     bar
    0.39
     Kraus
    0.38
    Activations Density 0.000%

    No Known Activations