© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30445
    Prev
    Next
    INDEX
    Explanations

    article structure

    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_10_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
     oversize
    0.49
     loafers
    0.49
    Mou
    0.48
     اضافی
    0.47
    M
    0.47
    diverse
    0.47
    N
    0.46
     meni
    0.46
     scars
    0.45
     contradictions
    0.45
    POSITIVE LOGITS
    ла
    0.56
    ты
    0.49
    я
    0.48
    ор
    0.47
     ="
    0.47
    х
    0.46
    ат
    0.45
    шь
    0.44
     ➤
    0.42
    вах
    0.42
    Activations Density 0.057%

    No Known Activations