© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171109
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ongoing
    0.57
    ongoing
    0.56
     Ongoing
    0.50
    Ongoing
    0.50
     চলমান
    0.42
    的需求
    0.42
     underway
    0.41
     высоко
    0.41
    HIGH
    0.41
    高
    0.40
    POSITIVE LOGITS
     наші
    0.54
     наши
    0.52
     our
    0.50
     нашим
    0.49
    我們的
    0.48
     આપણા
    0.47
     nuestras
    0.47
     nossos
    0.47
     ہمارے
    0.47
     nosso
    0.46
    Activations Density 0.001%

    No Known Activations