© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241837
    Prev
    Next
    INDEX
    Explanations

    "so are", "why", "what", "describe"

    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_25_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
     nonprofits
    0.28
     yerde
    0.26
    oubtedly
    0.25
    ค
    0.24
     μη
    0.24
    নিয়া
    0.24
    ใช
    0.24
     echte
    0.24
    essayer
    0.24
    ణ
    0.24
    POSITIVE LOGITS
     получа
    0.33
     обстоя
    0.26
     خارج
    0.26
     அறிய
    0.26
     đất
    0.25
     сен
    0.25
     dimensión
    0.25
     egyéb
    0.24
    ４
    0.24
    國家
    0.24
    Activations Density 0.006%

    No Known Activations