© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241259
    Prev
    Next
    INDEX
    Explanations

    1-888-373-7888

    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_40_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
     कॉल्ड
    0.39
     четвер
    0.38
    óp
    0.38
     abrog
    0.36
    空间
    0.36
    包
    0.35
    第四
    0.34
     Zulu
    0.33
    スン
    0.33
    Czech
    0.33
    POSITIVE LOGITS
     Lux
    0.41
    Particip
    0.41
    daki
    0.38
     Participate
    0.38
    ڈر
    0.37
     уча
    0.37
    idina
    0.36
    达
    0.36
     тря
    0.36
     設計
    0.36
    Activations Density 0.009%

    No Known Activations