© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101636
    Prev
    Next
    INDEX
    Explanations

    peace

    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_44_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
    
    0.43
     relax
    0.42
    Relax
    0.41
    ର
    0.40
     leisurely
    0.39
     Relax
    0.38
     casually
    0.38
     Chalmers
    0.38
     推
    0.37
     atmosfer
    0.36
    POSITIVE LOGITS
    镉
    0.38
     bel
    0.37
     Radius
    0.36
     दिक्
    0.36
    ativa
    0.36
     кислоты
    0.36
    ateness
    0.35
     বো
    0.35
    ဝ်
    0.35
    arns
    0.34
    Activations Density 0.002%

    No Known Activations