© 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. 83122
    Prev
    Next
    INDEX
    Explanations

    W

    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
    Negative Logits
    UN
    0.44
    மல
    0.42
    驼
    0.41
     probabil
    0.40
     هد
    0.38
    uminescent
    0.38
    mmss
    0.37
     globo
    0.37
     нео
    0.36
    udev
    0.36
    POSITIVE LOGITS
     PH
    0.39
    )||
    0.39
    表中
    0.39
     بج
    0.39
     Spagna
    0.38
     MF
    0.38
     McInt
    0.38
    BF
    0.37
     Roh
    0.37
     barn
    0.36
    Activations Density 0.006%

    No Known Activations