© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 849
    Prev
    Next
    INDEX
    Explanations

    definition of a concept

    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_39_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
    ैया
    0.41
     IA
    0.41
    kuensi
    0.39
     EDM
    0.38
     dosen
    0.38
     fut
    0.37
    brace
    0.37
    ylene
    0.37
    果
    0.37
    GC
    0.36
    POSITIVE LOGITS
    跛
    0.41
     ..
    0.39
     தேர்தலில்
    0.38
    ສຸດ
    0.38
     முழுக்க
    0.37
     JPanel
    0.37
    设置为
    0.37
    amant
    0.37
     Subdistrict
    0.37
    ?";
    0.36
    Activations Density 0.073%

    No Known Activations