© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132398
    Prev
    Next
    INDEX
    Explanations

    places and brands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     T
    0.56
    gil
    0.44
    T
    0.44
     Ali
    0.44
     elements
    0.43
     t
    0.43
     barking
    0.42
     ต
    0.40
     Al
    0.40
    Al
    0.40
    POSITIVE LOGITS
    ricies
    0.50
     ಕಂಪ
    0.43
    恝
    0.43
    LINEAR
    0.43
     Multip
    0.42
    Bounce
    0.42
     Bounce
    0.42
     McN
    0.39
    総合
    0.39
     графі
    0.39
    Activations Density 0.006%

    No Known Activations