© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247436
    Prev
    Next
    INDEX
    Explanations

    map, json, gin, vocab, environment

    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_40_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
    ែ
    0.41
     камер
    0.40
     каме
    0.38
    Subsec
    0.37
    箋
    0.37
     fuertes
    0.36
     veille
    0.35
     striated
    0.35
     kebak
    0.35
    Adv
    0.35
    POSITIVE LOGITS
    buds
    0.40
    ș
    0.40
    wer
    0.40
    ギリス
    0.39
     fibers
    0.37
    ندر
    0.36
     util
    0.36
    cJ
    0.35
    ABLISHED
    0.35
    мум
    0.35
    Activations Density 0.000%

    No Known Activations