© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197922
    Prev
    Next
    INDEX
    Explanations

    dreaming or dreams

    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_12_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
     ถ้า
    0.45
    ড্রিম
    0.45
     sogno
    0.44
    魇
    0.44
     rupani
    0.44
    夢
    0.44
     mimpi
    0.43
     Schlaf
    0.43
     geldi
    0.42
     Tenemos
    0.42
    POSITIVE LOGITS
    ologist
    0.43
    Currently
    0.43
    Researcher
    0.43
    Flow
    0.42
    Line
    0.41
    esty
    0.41
    Inst
    0.41
    ”).
    0.41
    á
    0.41
    ation
    0.41
    Activations Density 0.002%

    No Known Activations