© 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. 136257
    Prev
    Next
    INDEX
    Explanations

    come up with

    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
    ーストラ
    0.61
     regiões
    0.60
    ♘
    0.59
     বিবাহ
    0.59
    niejszych
    0.57
    currentTime
    0.57
    োত্তর
    0.57
    த்திலேயே
    0.57
     encoded
    0.56
     एच
    0.56
    POSITIVE LOGITS
     de
    0.70
    '
    0.65
    "
    0.64
    de
    0.59
    ”
    0.58
    1
    0.55
    5
    0.54
     t
    0.52
     that
    0.51
    ...
    0.51
    Activations Density 0.000%

    No Known Activations