© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46429
    Prev
    Next
    INDEX
    Explanations

    night or evening activities

    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_22_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
    我也
    0.48
    我会
    0.42
    ۰
    0.42
    ترف
    0.42
    BRUARY
    0.42
     Россию
    0.41
     міжнарод
    0.41
     러시아
    0.40
     рус
    0.40
     येणार
    0.40
    POSITIVE LOGITS
     features
    0.44
     horizontal
    0.41
    AutoHide
    0.40
     captivated
    0.38
     designated
    0.38
     characteristics
    0.38
     contenidos
    0.37
    寬
    0.37
     authentication
    0.37
     bytes
    0.36
    Activations Density 0.001%

    No Known Activations