© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 193966
    Prev
    Next
    INDEX
    Explanations

    years ago or mandate

    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_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    م
    0.68
    м
    0.64
    د
    0.58
    ح
    0.57
    1
    0.52
    يت
    0.50
    ش
    0.48
    Namara
    0.47
    ؤ
    0.47
    骏
    0.47
    POSITIVE LOGITS
     supposition
    0.55
     Wrapping
    0.52
     Ens
    0.51
     spiller
    0.50
     cuz
    0.49
     wrapping
    0.48
     marcador
    0.48
     لوبی
    0.47
     marshmallow
    0.47
     Keeping
    0.46
    Activations Density 0.000%

    No Known Activations