© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257105
    Prev
    Next
    INDEX
    Explanations

    from scratch or negative force

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    rieved
    0.46
     truck
    0.43
     doe
    0.42
     politely
    0.42
     irrigation
    0.41
    ποιη
    0.41
    瑪
    0.41
     woolen
    0.41
    িয়ন
    0.40
     kil
    0.40
    POSITIVE LOGITS
    ની
    0.38
     émer
    0.38
    osphäre
    0.38
     costruire
    0.38
    дон
    0.37
     梅
    0.36
    财经
    0.36
     отста
    0.35
     پیسو
    0.35
     pestaña
    0.35
    Activations Density 0.000%

    No Known Activations