© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131173
    Prev
    Next
    INDEX
    Explanations

    numbers, literals, or specific programs

    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
    ح
    0.47
     hall
    0.46
     fl
    0.45
    ت
    0.43
    त
    0.43
     formation
    0.41
    god
    0.41
    graf
    0.41
    க
    0.41
     vibrates
    0.40
    POSITIVE LOGITS
     перспекти
    0.51
     آنچه
    0.51
     అన్ని
    0.48
     محیط
    0.48
     प्राथमिकता
    0.48
     Опера
    0.48
     RESPONSE
    0.47
     Diagnostics
    0.47
     специфи
    0.46
    ሷ
    0.46
    Activations Density 0.000%

    No Known Activations