© 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
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 129976
    Prev
    Next
    INDEX
    Explanations

    then followed by something new

    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_25_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
    许多
    0.35
    ∈</
    0.35
     следующих
    0.34
    assist
    0.34
     rémun
    0.34
    യ്ക്ക
    0.33
     ඔබට
    0.33
    >(_
    0.33
    names
    0.33
    ᓛ
    0.33
    POSITIVE LOGITS
     hola
    0.40
     Boc
    0.38
     bounds
    0.38
     quente
    0.38
     Hola
    0.38
     pront
    0.38
    िल्स
    0.37
    uce
    0.37
     فور
    0.37
    ੁ
    0.36
    Activations Density 0.002%

    No Known Activations