© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219428
    Prev
    Next
    INDEX
    Explanations

    URLs with non-English characters

    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_31_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
     iterations
    0.38
     متغير
    0.38
    PRI
    0.37
     PRI
    0.37
    伦敦
    0.37
    擞
    0.36
    тения
    0.35
    珑
    0.35
     আপডেট
    0.35
     {},
    0.35
    POSITIVE LOGITS
    一大
    0.38
     ಮನ
    0.37
     germ
    0.35
     aliado
    0.35
    emet
    0.35
     lit
    0.34
    conder
    0.34
     piante
    0.34
    増加
    0.34
    iej
    0.34
    Activations Density 0.000%

    No Known Activations