© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85314
    Prev
    Next
    INDEX
    Explanations

    residence permit

    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_3_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
     SATA
    0.67
     >=
    0.67
     famiglia
    0.67
     perpetually
    0.65
     famille
    0.65
     financiera
    0.64
     fraudulently
    0.64
     transcendent
    0.64
    .
    0.64
     waarde
    0.63
    POSITIVE LOGITS
    ร
    0.64
    ழ
    0.63
    া
    0.62
    inning
    0.61
    ל
    0.61
    ল
    0.60
    بر
    0.59
    ص
    0.56
    0
    0.56
    tense
    0.55
    Activations Density 0.000%

    No Known Activations