© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199985
    Prev
    Next
    INDEX
    Explanations

    Latvian place names (Pils, Melnais) and Russian endings (ского)

    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_15_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
     alemão
    0.53
    Ꮡ
    0.52
    время
    0.51
    เค
    0.50
    "%(
    0.48
     మొదటి
    0.48
    颞
    0.48
    rą
    0.48
     ஸ்ரீ
    0.47
    тием
    0.47
    POSITIVE LOGITS
     includes
    0.52
     residential
    0.52
     testifies
    0.50
     pizzeria
    0.50
     children
    0.50
    itele
    0.49
     ensures
    0.48
     define
    0.47
     dispers
    0.47
     spotlight
    0.47
    Activations Density 0.000%

    No Known Activations