© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115115
    Prev
    Next
    INDEX
    Explanations

    locations and offices

    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_27_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
     persuasion
    0.29
     ಜಾ
    0.27
     спра
    0.27
    ිය
    0.27
    Parsed
    0.27
    прав
    0.26
    Performance
    0.26
    Violet
    0.26
    侠
    0.26
     Truth
    0.26
    POSITIVE LOGITS
     headquarters
    0.44
    总部
    0.41
     fasilitas
    0.37
     මෙම
    0.34
    办公
    0.34
     कर्मचारियों
    0.33
     அலுவலக
    0.33
     ეს
    0.33
     biblioteca
    0.33
     大阪
    0.33
    Activations Density 0.000%

    No Known Activations