© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117862
    Prev
    Next
    INDEX
    Explanations

    .generation, .rate, .histogram, .paragraph, .monte

    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_27_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
    鐒
    0.43
     potenc
    0.42
     tigris
    0.41
    ंत
    0.39
     Meesho
    0.39
     aprovechar
    0.39
    жали
    0.38
     Nizam
    0.38
    ⼒
    0.37
     দেখেছিল
    0.36
    POSITIVE LOGITS
     간단
    0.36
     rarely
    0.35
    ایط
    0.35
    ="__
    0.33
    BRUARY
    0.33
    di
    0.32
     fà
    0.32
    روط
    0.32
     seldom
    0.32
    ٻ
    0.32
    Activations Density 0.000%

    No Known Activations