© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54687
    Prev
    Next
    INDEX
    Explanations

    "the" or "United States"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_30_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
    銷
    0.40
    CRY
    0.36
     গুরু
    0.35
     congruent
    0.35
     तस्करी
    0.35
    承
    0.35
     ordinal
    0.34
    فرج
    0.34
    touchstart
    0.34
     grounded
    0.34
    POSITIVE LOGITS
    ujte
    0.38
    ">${
    0.38
     fuerzas
    0.36
     Shortcuts
    0.35
     পরিষ
    0.35
     Various
    0.35
     atuais
    0.34
    ike
    0.34
     derivs
    0.34
    reuses
    0.34
    Activations Density 0.016%

    No Known Activations