© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200009
    Prev
    Next
    INDEX
    Explanations

    school year begins

    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_27_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
     daytime
    0.42
    Giải
    0.41
    Saturday
    0.40
    িপ্ত
    0.38
     weekday
    0.36
    рафон
    0.36
    ocene
    0.35
    пки
    0.35
    αιρε
    0.35
    站
    0.35
    POSITIVE LOGITS
     Marion
    0.40
     informally
    0.38
     opacity
    0.38
     红
    0.37
     Geometric
    0.36
     Leuk
    0.36
     Cerc
    0.36
    textField
    0.35
     Emotion
    0.35
     cirk
    0.35
    Activations Density 0.001%

    No Known Activations