© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57641
    Prev
    Next
    INDEX
    Explanations

    6

    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_59_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
     M
    0.59
    م
    0.48
    To
    0.45
    M
    0.42
    m
    0.41
     m
    0.40
     To
    0.40
     Value
    0.40
    man
    0.39
     М
    0.39
    POSITIVE LOGITS
     Mo
    1.15
     MO
    1.15
    莫
    1.13
    Mo
    1.10
     Moh
    1.09
     Mö
    1.08
     Moj
    1.05
     โม
    1.05
    Moj
    1.05
     Мо
    1.05
    Activations Density 0.004%

    No Known Activations