© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205520
    Prev
    Next
    INDEX
    Explanations

    points following number

    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_20_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
     perspectives
    0.39
    ListIterator
    0.38
    كنولوج
    0.38
     careers
    0.37
    careers
    0.35
    ◸
    0.35
     resolutions
    0.35
     traditions
    0.34
    ীবনী
    0.34
     Chopra
    0.33
    POSITIVE LOGITS
     quoi
    0.43
     T
    0.37
     mę
    0.37
     सर
    0.36
     ગે
    0.36
     lập
    0.36
     Prevalence
    0.35
     Disable
    0.35
     edil
    0.35
    ப்பதற்காக
    0.35
    Activations Density 0.000%

    No Known Activations