© 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. 7062
    Prev
    Next
    INDEX
    Explanations

    purpose or nature

    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
    qh
    0.38
     thì
    0.35
    sheep
    0.35
    宰
    0.34
     Thì
    0.34
     ફો
    0.34
    デニム
    0.34
    genes
    0.33
     Pilot
    0.33
     اعتق
    0.33
    POSITIVE LOGITS
    ندوق
    0.40
    ሚ
    0.38
    преде
    0.37
    ivari
    0.37
     প্রত্যা
    0.37
    ίος
    0.36
    ביל
    0.36
    水泥
    0.36
    <bbox>
    0.35
     tiresome
    0.35
    Activations Density 0.443%

    No Known Activations