© 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. 15797
    Prev
    Next
    INDEX
    Explanations

    click, argparse, GUI, download

    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
     Bedford
    0.44
     pria
    0.43
     prolongation
    0.40
     hombres
    0.39
    
    0.38
     مرد
    0.38
     strong
    0.37
     divers
    0.36
     শিবির
    0.36
     mView
    0.36
    POSITIVE LOGITS
    paren
    0.37
    自然
    0.36
    ₲
    0.36
     ഗോ
    0.36
    Snake
    0.36
    flatMap
    0.35
    boss
    0.34
     Apare
    0.34
    Teri
    0.34
    妍
    0.34
    Activations Density 0.001%

    No Known Activations