© 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. 151823
    Prev
    Next
    INDEX
    Explanations

    st

    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
    ខ
    0.38
    umont
    0.38
     bushels
    0.37
    𒄑
    0.37
    ਠ
    0.36
     बनने
    0.36
    '."
    0.36
    
    0.36
     הן
    0.35
     struts
    0.35
    POSITIVE LOGITS
     Stake
    1.80
    Stake
    1.72
     stake
    1.71
    stake
    1.59
     stakeholder
    1.58
     stakeholders
    1.39
     staked
    1.29
     staking
    1.22
    staking
    0.99
     stakes
    0.98
    Activations Density 0.000%

    No Known Activations