© 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. 212131
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
     ricerca
    0.47
    rocin
    0.47
    ocysts
    0.47
    heureusement
    0.46
     Leadership
    0.46
    ⵍ
    0.45
    িতাম
    0.44
    Bev
    0.44
    राब
    0.44
     Duv
    0.44
    POSITIVE LOGITS
     transversely
    0.49
     ο
    0.47
     ).
    0.42
     зада
    0.42
     autores
    0.42
     ਆਪਣ
    0.42
     inherently
    0.41
    ⌀
    0.41
     barrier
    0.41
     ഒന്നും
    0.40
    Activations Density 0.000%

    No Known Activations