© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6641
    Prev
    Next
    INDEX
    Explanations

    Get-Service/Write-

    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_40_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
     CITY
    0.38
     authorities
    0.36
     "
    0.35
     FED
    0.35
     بط
    0.35
     XY
    0.35
     xy
    0.34
     experts
    0.34
     tri
    0.32
     HA
    0.32
    POSITIVE LOGITS
    Ϫ
    0.47
    -​
    0.40
    ‐
    0.37
    −
    0.36
    ‒
    0.36
    Release
    0.35
    -
    0.35
    ˗
    0.34
    -=
    0.33
    ‑
    0.33
    Activations Density 0.012%

    No Known Activations