© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145254
    Prev
    Next
    INDEX
    Explanations

    antennaantennas

    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_18_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
    ué
    0.51
     niece
    0.46
     dosage
    0.46
    ∅
    0.46
    ött
    0.45
     таких
    0.45
     quirky
    0.45
     sporadic
    0.45
    inne
    0.44
     takich
    0.44
    POSITIVE LOGITS
    বারের
    0.47
     bun
    0.43
    ئه
    0.40
     yaşı
    0.40
     தங்க
    0.40
     vuln
    0.40
    恰
    0.40
    thand
    0.39
     tenders
    0.39
     t
    0.39
    Activations Density 0.000%

    No Known Activations