© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85424
    Prev
    Next
    INDEX
    Explanations

    how to describe or implement

    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fæ
    0.54
    ā
    0.53
     ove
    0.52
     svi
    0.50
     tilbake
    0.48
     influx
    0.46
     overclock
    0.45
     åter
    0.45
    ì
    0.45
     præ
    0.44
    POSITIVE LOGITS
     Maps
    0.54
     Drury
    0.51
     Harding
    0.50
     Armand
    0.50
    де
    0.49
     Hard
    0.49
    maps
    0.48
     ನಗರ
    0.48
     Moulton
    0.47
     Downtown
    0.47
    Activations Density 0.000%

    No Known Activations