© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21514
    Prev
    Next
    INDEX
    Explanations

    every other

    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_56_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
     every
    2.89
     Every
    2.84
    Every
    2.78
    every
    2.55
     ogni
    2.33
     setiap
    2.17
    每
    2.03
     Setiap
    2.00
     एवरी
    1.95
    ทุก
    1.88
    POSITIVE LOGITS
    কোত্তর
    0.37
    striction
    0.33
    ͝
    0.32
    曰
    0.32
    ̯
    0.32
     kullanım
    0.31
     sagittis
    0.31
    otro
    0.31
    自治
    0.31
    ү
    0.30
    Activations Density 0.018%

    No Known Activations