© 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. 245462
    Prev
    Next
    INDEX
    Explanations

    flow of goods

    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
     Post
    0.43
     Ά
    0.43
     post
    0.38
    post
    0.37
     bona
    0.37
    アイ
    0.36
     пост
    0.36
     Ayat
    0.36
    æ
    0.36
     Alt
    0.35
    POSITIVE LOGITS
     specialists
    0.45
     mLocation
    0.45
     CONSTRUCTION
    0.42
    Construction
    0.40
    Locations
    0.40
     MAKEINTRESOURCE
    0.40
    locations
    0.40
     مخالف
    0.39
    भीर
    0.39
     tortor
    0.38
    Activations Density 0.003%

    No Known Activations