© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67994
    Prev
    Next
    INDEX
    Explanations

    A

    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_51_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
     Hep
    0.42
    Heating
    0.42
    构
    0.40
    Hep
    0.40
    ḳ
    0.40
     ಆದ
    0.39
    陉
    0.39
     Egan
    0.38
    Bryan
    0.38
    രായ
    0.37
    POSITIVE LOGITS
    usak
    0.40
     σα
    0.37
    رت
    0.37
    펑
    0.36
    娄
    0.36
     Sach
    0.36
    lowing
    0.35
     feeds
    0.35
    まつ
    0.35
    峦
    0.35
    Activations Density 0.002%

    No Known Activations