© 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. 31002
    Prev
    Next
    INDEX
    Explanations

    dag

    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
    Not in Any Lists

    No Comments

    Negative Logits
     سنت
    0.47
    ERNAL
    0.42
    ALA
    0.41
     باکس
    0.41
    쌔
    0.41
     Ala
    0.41
     ਵਾਲ
    0.41
     ದಾಖ
    0.40
     कार्ब
    0.40
     बीन
    0.40
    POSITIVE LOGITS
     P
    0.44
    dag
    0.40
     dag
    0.39
     Dag
    0.39
    bo
    0.38
     appreciate
    0.38
     huo
    0.38
     anharmonic
    0.37
    ili
    0.37
    Dag
    0.36
    Activations Density 0.002%

    No Known Activations