© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232065
    Prev
    Next
    INDEX
    Explanations

    employee counts

    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_32_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
    觛
    0.41
    Spoiler
    0.38
    تهم
    0.36
     Gente
    0.35
     Koenig
    0.35
    Guarantee
    0.35
    ματο
    0.34
    тных
    0.34
     spoiler
    0.34
    SIN
    0.34
    POSITIVE LOGITS
     REC
    0.40
    REC
    0.39
    ሁ
    0.39
    rents
    0.38
     APC
    0.37
     YOK
    0.37
    學
    0.37
     association
    0.36
     அப்ப
    0.36
    ifax
    0.35
    Activations Density 0.001%

    No Known Activations