© 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. 83249
    Prev
    Next
    INDEX
    Explanations

    URLs websites

    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
     चैन
    0.42
     раз
    0.40
    рд
    0.38
     Elmer
    0.37
    華
    0.37
     տար
    0.36
    Mac
    0.35
    MAC
    0.35
     dimensión
    0.35
    mac
    0.35
    POSITIVE LOGITS
     Poets
    0.40
     ضر
    0.39
    starts
    0.38
     todd
    0.38
    ኒ
    0.38
     ign
    0.38
     stockp
    0.37
     Declan
    0.37
     꾸
    0.36
     Joanne
    0.36
    Activations Density 0.000%

    No Known Activations