© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54736
    Prev
    Next
    INDEX
    Explanations

    film photography, Polaroid, Kodachrome, Ektachrome, grainy, faded image

    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_31_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
    Mas
    0.40
    Cookie
    0.38
    Murphy
    0.38
     exclaimed
    0.37
     Murphy
    0.36
    Camping
    0.36
    🎁
    0.36
     GUI
    0.35
     exquisite
    0.35
     ڈاؤن
    0.35
    POSITIVE LOGITS
     лабора
    0.40
     转
    0.39
     legendary
    0.39
     mers
    0.39
     porto
    0.38
     mirror
    0.38
     Brahm
    0.38
    转
    0.38
    ющий
    0.37
     laser
    0.37
    Activations Density 0.004%

    No Known Activations