© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8537
    Prev
    Next
    INDEX
    Explanations

    opening hours

    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_13_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
     laptop
    0.36
     plaat
    0.34
    i
    0.34
     vaginal
    0.33
    م
    0.33
     可
    0.31
    in
    0.30
     all
    0.30
     suitcase
    0.30
    POSITIVE LOGITS
    prnewswire
    0.42
    starttime
    0.40
     Биз
    0.40
    ᱗
    0.40
    営業時間
    0.38
    फेसर
    0.38
    tiin
    0.38
    ʬ
    0.37
     ቀ
    0.37
    measuredangle
    0.37
    Activations Density 0.065%

    No Known Activations