© 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. 193653
    Prev
    Next
    INDEX
    Explanations

    presents alternatives

    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
    Negative Logits
     tudo
    0.54
     négy
    0.53
     nejen
    0.52
    ৈত্র
    0.49
    𝗂
    0.49
     quatro
    0.49
     fascist
    0.48
    tudo
    0.47
     sechs
    0.46
     pás
    0.45
    POSITIVE LOGITS
    Publisher
    0.46
    Rem
    0.46
    Jan
    0.45
    Enum
    0.44
    Report
    0.43
    了起来
    0.43
    En
    0.43
    N
    0.42
    Edit
    0.42
    upu
    0.41
    Activations Density 0.028%

    No Known Activations