© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170985
    Prev
    Next
    INDEX
    Explanations

    the

    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_56_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
     принцип
    0.53
    原则
    0.44
    нцип
    0.42
    ّٰ
    0.42
     اصول
    0.41
    }(-\
    0.41
     principe
    0.41
     основных
    0.40
    ᱔
    0.40
     principio
    0.40
    POSITIVE LOGITS
     addition
    0.56
    addition
    0.55
     Conc
    0.53
    Addition
    0.47
    conc
    0.46
    Conc
    0.46
     conc
    0.44
     Addition
    0.43
     additions
    0.37
    ཊ
    0.36
    Activations Density 0.001%

    No Known Activations