© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195589
    Prev
    Next
    INDEX
    Explanations

    non-latin scripts

    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_15_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
    s
    0.65
    𝐂
    0.55
    س
    0.53
    FIF
    0.49
     iw
    0.48
    С
    0.48
     immig
    0.48
     ont
    0.47
     rozwoju
    0.46
    𝐀
    0.46
    POSITIVE LOGITS
     ჰ
    0.56
    oki
    0.53
    codingPath
    0.52
    asted
    0.52
    ки
    0.51
     ლი
    0.50
    iciones
    0.49
     secciones
    0.49
    ismo
    0.49
     குறைந்த
    0.49
    Activations Density 0.000%

    No Known Activations