© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221306
    Prev
    Next
    INDEX
    Explanations

    programs offered

    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_31_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
     Carefully
    0.40
     अनुदान
    0.40
    loans
    0.40
     கடன்
    0.38
    moving
    0.38
     Moving
    0.38
    贷
    0.38
     moving
    0.37
    Regulatory
    0.37
    Mom
    0.37
    POSITIVE LOGITS
     victim
    0.43
     చెప్పు
    0.42
     Nası
    0.41
     prominence
    0.40
     hiển
    0.38
     haci
    0.38
     Priscilla
    0.37
    炡
    0.37
     souff
    0.37
    被害
    0.37
    Activations Density 0.001%

    No Known Activations