© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233940
    Prev
    Next
    INDEX
    Explanations

    legal amendments

    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_46_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
     abstracts
    0.31
     বাকি
    0.31
     omit
    0.30
     Изда
    0.30
    produk
    0.30
    /^
    0.30
    មី
    0.29
    薹
    0.29
     amending
    0.29
    Кор
    0.29
    POSITIVE LOGITS
     postwar
    0.37
     post
    0.32
    ポスト
    0.31
    aliana
    0.31
     الاشت
    0.30
     uncont
    0.30
     നിറഞ്ഞ
    0.30
     Jacobson
    0.29
     Defense
    0.29
     gob
    0.29
    Activations Density 0.000%

    No Known Activations