© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136007
    Prev
    Next
    INDEX
    Explanations

    popsicles

    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_12_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
     setSearch
    0.56
     palestra
    0.54
    astore
    0.54
    Essay
    0.53
    ou
    0.53
    先
    0.52
    Le
    0.52
     Luciano
    0.52
    谊
    0.52
    terraform
    0.51
    POSITIVE LOGITS
     \
    0.61
     деца
    0.47
     immun
    0.46
     سنی
    0.46
     Pol
    0.46
    \},
    0.46
    お子
    0.45
     çocuğ
    0.45
    ฤษ
    0.45
     decimal
    0.44
    Activations Density 0.001%

    No Known Activations