© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5212
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     actif
    0.45
     актив
    0.44
     active
    0.43
     കാലാവ
    0.42
    Oj
    0.39
    ണ്ണി
    0.39
     ACTIVE
    0.39
    褰
    0.39
     Active
    0.38
     aktif
    0.38
    POSITIVE LOGITS
     castings
    0.36
     holding
    0.36
     holds
    0.36
    edia
    0.35
    成就
    0.35
     Holding
    0.34
     col
    0.33
     subcontract
    0.33
     কল
    0.33
    hspace
    0.32
    Activations Density 0.000%

    No Known Activations