© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134137
    Prev
    Next
    INDEX
    Explanations

    I cannot help

    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_50_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
     CO
    0.45
    <0xAA>
    0.44
    CO
    0.42
    mml
    0.41
     Co
    0.40
     ко
    0.39
     Ada
    0.39
    COC
    0.38
    co
    0.38
     ভোগের
    0.38
    POSITIVE LOGITS
     excuses
    0.48
    Ku
    0.45
    ham
    0.44
    kbar
    0.44
     Duncan
    0.43
    Duncan
    0.43
     excuse
    0.42
    ク
    0.41
    Den
    0.41
    Gi
    0.41
    Activations Density 0.014%

    No Known Activations