© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115141
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_27_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
    慚
    0.42
     محاس
    0.36
     पनि
    0.35
    èle
    0.34
     Συ
    0.34
     subv
    0.34
     jual
    0.34
     gru
    0.33
     []),
    0.33
    гү
    0.33
    POSITIVE LOGITS
    blueprint
    0.41
    BLUE
    0.39
    arkeit
    0.38
    messages
    0.38
    akses
    0.37
     क्रांतिक
    0.37
    rikt
    0.36
    rape
    0.36
     সমাপ্ত
    0.36
    tort
    0.36
    Activations Density 0.000%

    No Known Activations