© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80422
    Prev
    Next
    INDEX
    Explanations

    German words and abbreviations

    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_53_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
     w
    0.68
     W
    0.57
    w
    0.51
     blend
    0.49
    wString
    0.46
    ว
    0.45
    Ｗ
    0.44
    W
    0.43
    MW
    0.43
     blends
    0.42
    POSITIVE LOGITS
    اح
    0.45
     الاح
    0.43
     anh
    0.40
    hog
    0.40
     Hollis
    0.39
     hoga
    0.39
    рее
    0.38
     Holes
    0.38
     aguj
    0.38
     đêm
    0.37
    Activations Density 0.017%

    No Known Activations