© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155600
    Prev
    Next
    INDEX
    Explanations

    word problems

    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_60_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
     waning
    0.46
     lagging
    0.45
     experimentation
    0.43
     tapering
    0.40
     lessening
    0.40
    <0x0D>
    0.40
     grasping
    0.40
     ५
    0.39
     slipping
    0.39
     canceling
    0.38
    POSITIVE LOGITS
     OPEN
    0.50
    OPEN
    0.49
    MODEL
    0.48
     HOW
    0.47
     SOME
    0.47
     KEEP
    0.47
     report
    0.46
    BUT
    0.46
    keep
    0.46
    HOW
    0.45
    Activations Density 0.003%

    No Known Activations