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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 15271
    Prev
    Next
    INDEX
    Explanations

    Subroutines and Subs

    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
    omyc
    0.42
     शिव
    0.37
     انگری
    0.37
     உச்ச
    0.36
     фай
    0.36
     fichiers
    0.35
     évo
    0.35
     ቁ
    0.34
    })^{
    0.33
     Inlet
    0.33
    POSITIVE LOGITS
     Sub
    1.98
    Sub
    1.95
     submarine
    1.88
     sub
    1.83
     суб
    1.83
    sub
    1.80
     subs
    1.70
     SUB
    1.66
    SUB
    1.62
     submarines
    1.62
    Activations Density 0.043%

    No Known Activations