© 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. 77119
    Prev
    Next
    INDEX
    Explanations

    mer

    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
     yah
    0.67
     Y
    0.66
     ইয়
    0.64
    Yah
    0.63
     y
    0.61
     ইয়
    0.61
     Yah
    0.58
     Is
    0.56
    Y
    0.55
     ય
    0.52
    POSITIVE LOGITS
     mer
    0.55
     meri
    0.50
    meri
    0.48
     bac
    0.47
     mere
    0.44
     merchandising
    0.42
     мер
    0.40
     mér
    0.39
     mera
    0.39
    Mere
    0.39
    Activations Density 0.025%

    No Known Activations