© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30696
    Prev
    Next
    INDEX
    Explanations

    cost

    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_50_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
    随
    0.40
    폄
    0.37
    хол
    0.35
    ментов
    0.34
     Kham
    0.34
     solder
    0.33
    irm
    0.33
    කර
    0.33
    铵
    0.32
     xen
    0.32
    POSITIVE LOGITS
    Cost
    3.00
     Cost
    2.95
    cost
    2.86
     cost
    2.78
    COST
    2.73
     kost
    2.67
     COST
    2.67
     costa
    2.55
     Kost
    2.52
    Kost
    2.52
    Activations Density 0.020%

    No Known Activations