© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3062
    Prev
    Next
    INDEX
    Explanations

    description or explanation

    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_39_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
     дороге
    0.41
    ೆಯಿಂದ
    0.39
    SubDirectoryPath
    0.38
     guardia
    0.38
     Ваши
    0.37
     osmotic
    0.37
    绀
    0.37
     mexican
    0.36
    များကို
    0.36
    ర్జాతీయ
    0.35
    POSITIVE LOGITS
     revolve
    0.42
    anh
    0.41
     exert
    0.41
     revolved
    0.41
     revolves
    0.39
     terdiri
    0.38
     conveyed
    0.37
     ,
    0.37
     consists
    0.36
     select
    0.36
    Activations Density 0.142%

    No Known Activations